0000000000000000000000000000000000000000 e3bc6c8f8247bd8f0e00189004c600e939ee0ada Niki Hasrati <nhasrati@uwaterloo.ca> 1743381667 -0400	commit (initial): First commit: added support for activation steering
e3bc6c8f8247bd8f0e00189004c600e939ee0ada e3bc6c8f8247bd8f0e00189004c600e939ee0ada Niki Hasrati <nhasrati@uwaterloo.ca> 1743381680 -0400	Branch: renamed refs/heads/master to refs/heads/main
e3bc6c8f8247bd8f0e00189004c600e939ee0ada 933dd93f002694162f8cf8f53430119e7f2a9895 Niki Hasrati <nhasrati@uwaterloo.ca> 1743384167 -0400	commit: Added requirements file
933dd93f002694162f8cf8f53430119e7f2a9895 f1bed5fbc3f499b9416715b0ad53317196b18288 Niki Hasrati <nhasrati@uwaterloo.ca> 1743387516 -0400	commit: Added gitignore file
f1bed5fbc3f499b9416715b0ad53317196b18288 0ebb794998a3af0a9e6064e521e1d4d71b2f0e9f Niki Hasrati <nhasrati@uwaterloo.ca> 1743610230 -0400	commit: Updated requirements
0ebb794998a3af0a9e6064e521e1d4d71b2f0e9f 35f362ddc2677dfc810726225752978b59e6928b Niki Hasrati <nhasrati@uwaterloo.ca> 1743610647 -0400	pull: Fast-forward
35f362ddc2677dfc810726225752978b59e6928b e15a2f34fedae5e3a30a58122cf26c2e3968b2c5 Niki Hasrati <nhasrati@uwaterloo.ca> 1743610746 -0400	commit: Updated gitignore
e15a2f34fedae5e3a30a58122cf26c2e3968b2c5 ef56096d799b362f564bbca0c4552a4f9315eff5 Niki Hasrati <nhasrati@uwaterloo.ca> 1743610802 -0400	commit: Updated README
ef56096d799b362f564bbca0c4552a4f9315eff5 32deb42089ab641ddabf324543f65f58e91ae34c Niki Hasrati <nhasrati@uwaterloo.ca> 1743610980 -0400	commit: Got Jailbreak judge working on babel
32deb42089ab641ddabf324543f65f58e91ae34c a536db3c9ef6c974eb0dbc19a9adbadec9b151df Niki Hasrati <nhasrati@uwaterloo.ca> 1743611513 -0400	commit: Removed unnecessary imports
a536db3c9ef6c974eb0dbc19a9adbadec9b151df d54a915420d8491d54a5d53154b1458c69a6bb42 Niki Hasrati <nhasrati@uwaterloo.ca> 1743614154 -0400	commit: Added helper function
d54a915420d8491d54a5d53154b1458c69a6bb42 e00aa98acde93f93bf89d65d9756d3a7d34d03c8 Niki Hasrati <nhasrati@uwaterloo.ca> 1743614180 -0400	commit: Removed refusal direction file
e00aa98acde93f93bf89d65d9756d3a7d34d03c8 f410b00f5b280128c36072c0b4006c1d17be1302 Niki Hasrati <nhasrati@uwaterloo.ca> 1743614373 -0400	commit: Added gitattributes file:
f410b00f5b280128c36072c0b4006c1d17be1302 c3745a8558f913f41b9df05357047a3c640d45a5 Niki Hasrati <nhasrati@uwaterloo.ca> 1743614397 -0400	commit: Added dataset files
c3745a8558f913f41b9df05357047a3c640d45a5 5d446fad0ea990feb6029e66be7bd5dbfce947c0 Niki Hasrati <nhasrati@uwaterloo.ca> 1743616308 -0400	commit: Added data
5d446fad0ea990feb6029e66be7bd5dbfce947c0 97db0a9121d672bd8f542802c84337873e31888d Niki Hasrati <nhasrati@uwaterloo.ca> 1743620697 -0400	commit: Moved some files
97db0a9121d672bd8f542802c84337873e31888d c66b14c4ffe2b3fb6a903b378cc4d4ac216a4c0f Niki Hasrati <nhasrati@uwaterloo.ca> 1743624090 -0400	commit: Fixed some bugs
c66b14c4ffe2b3fb6a903b378cc4d4ac216a4c0f a584f89cb9f0fe06e2ef091bddcbb41b293a8e48 Niki Hasrati <nhasrati@uwaterloo.ca> 1743639681 -0400	commit: Added code for generating and evaluating completions
a584f89cb9f0fe06e2ef091bddcbb41b293a8e48 f8b7a0d5faccfb45c1c25110e09438082260b1fb Niki Hasrati <nhasrati@uwaterloo.ca> 1743639910 -0400	commit: Updated README
f8b7a0d5faccfb45c1c25110e09438082260b1fb 1ce67ce3adaf234d1392fcc7cc8c5316bf471208 Niki Hasrati <nhasrati@uwaterloo.ca> 1743640108 -0400	commit: Update submodule
1ce67ce3adaf234d1392fcc7cc8c5316bf471208 42ebb2684e8c4b8bbb82163da5390785ccda33b3 Niki Hasrati <nhasrati@uwaterloo.ca> 1743707348 -0400	commit: Updated code for generating and evaluating completions
42ebb2684e8c4b8bbb82163da5390785ccda33b3 808f618d4240c809b430f361f9a6d24404f852ac Niki Hasrati <nhasrati@uwaterloo.ca> 1743707453 -0400	commit: Updated submodule
808f618d4240c809b430f361f9a6d24404f852ac ec0c03d78058e2302d872dfa299b351fdd699d5e Niki Hasrati <nhasrati@uwaterloo.ca> 1743707562 -0400	commit: Added sbatch scripts
ec0c03d78058e2302d872dfa299b351fdd699d5e 8f160325e29a38fe1fd239fa502ce8aeb1f69a4a Niki Hasrati <nhasrati@uwaterloo.ca> 1743710166 -0400	commit: Updated submodule
8f160325e29a38fe1fd239fa502ce8aeb1f69a4a 83d7babdda6ad63462d44cb09adb69ea570add83 Niki Hasrati <nhasrati@uwaterloo.ca> 1743710213 -0400	commit: Added some code for data analysis
83d7babdda6ad63462d44cb09adb69ea570add83 6e88052321fc8cc493ea771c938ff8ff77b6c8c8 Niki Hasrati <nhasrati@uwaterloo.ca> 1743710257 -0400	commit: Updated gitignore file
6e88052321fc8cc493ea771c938ff8ff77b6c8c8 9977abb493958c3ca1dd4f16d8d16c569d43ae5f Niki Hasrati <nhasrati@uwaterloo.ca> 1743710472 -0400	commit: Updated data analysis file
9977abb493958c3ca1dd4f16d8d16c569d43ae5f ed623819020c110aa2f24af371f1a30267bb038d Niki Hasrati <nhasrati@uwaterloo.ca> 1743796651 -0400	commit: Updated Config with more file paths
ed623819020c110aa2f24af371f1a30267bb038d 2f20b180d91156ab89376a1c308a5321e253a966 Niki Hasrati <nhasrati@uwaterloo.ca> 1743796731 -0400	commit: Fixed bug with extracting activations
2f20b180d91156ab89376a1c308a5321e253a966 4a12470a449f600979dc99c2a7a33dcdd4cbad3d Niki Hasrati <nhasrati@uwaterloo.ca> 1743796799 -0400	commit: Added support for qwen 1.8b model
4a12470a449f600979dc99c2a7a33dcdd4cbad3d 842f06ab9079ac0dd055a384ba3763f7fc8fc318 Niki Hasrati <nhasrati@uwaterloo.ca> 1743796818 -0400	commit: Added utils functionality
842f06ab9079ac0dd055a384ba3763f7fc8fc318 e81542bbda12ff64b814324a9ca4bd170b29004f Niki Hasrati <nhasrati@uwaterloo.ca> 1743796866 -0400	commit: Added functionality for saving activations
e81542bbda12ff64b814324a9ca4bd170b29004f e445c5e4bc56c21679136d7d1129da08501be99a Niki Hasrati <nhasrati@uwaterloo.ca> 1743880385 -0400	commit: Update readme
e445c5e4bc56c21679136d7d1129da08501be99a e9e4a5ac778aba74ed9e48c454a807e5f34e47d5 Niki Hasrati <nhasrati@uwaterloo.ca> 1743880433 -0400	commit: Fixed bug with activations
e9e4a5ac778aba74ed9e48c454a807e5f34e47d5 d5b6c9f2e47c7598bddafe68cb17c4f07e33dd7e Niki Hasrati <nhasrati@uwaterloo.ca> 1743880450 -0400	commit: Updated pipeline
d5b6c9f2e47c7598bddafe68cb17c4f07e33dd7e deb02a3fd34148a55a25b4aff53de12722c46142 Niki Hasrati <nhasrati@uwaterloo.ca> 1743880483 -0400	commit: Added data analysis functionalities
deb02a3fd34148a55a25b4aff53de12722c46142 adfbe4081d0631edd09dcbb8f5339366a6607166 Niki Hasrati <nhasrati@uwaterloo.ca> 1743880499 -0400	commit: Added script for saving activations
adfbe4081d0631edd09dcbb8f5339366a6607166 9ea524953bfd2ceb111bde8bd087b2816bcb4924 Niki Hasrati <nhasrati@uwaterloo.ca> 1744667169 -0400	commit: Updated readme file
9ea524953bfd2ceb111bde8bd087b2816bcb4924 927ec215a2dd51f4a1377ac9ccd6f20d28fcd957 Niki Hasrati <nhasrati@uwaterloo.ca> 1744667288 -0400	commit: Fixed bug with activations
927ec215a2dd51f4a1377ac9ccd6f20d28fcd957 940fa2a56e83048463e28c9502e58be50af0f9c3 Niki Hasrati <nhasrati@uwaterloo.ca> 1744667325 -0400	commit: Updated data analysis code
940fa2a56e83048463e28c9502e58be50af0f9c3 160c6738d2495e99751b81f8b7c5c80df10de68b Niki Hasrati <nhasrati@uwaterloo.ca> 1744667341 -0400	commit: Added support for Vicuna
160c6738d2495e99751b81f8b7c5c80df10de68b b528e8b179aedd05f7ce90f822060b7afe382bec Niki Hasrati <nhasrati@uwaterloo.ca> 1744667364 -0400	commit: Added support for qwen
b528e8b179aedd05f7ce90f822060b7afe382bec b3a81456264658e25b047228d86e2edb46f574ac Niki Hasrati <nhasrati@uwaterloo.ca> 1744744549 -0400	commit: Fixed bug with saving activations
b3a81456264658e25b047228d86e2edb46f574ac 6ab20a489faa6b28284d3dec790f7b8a85842a4c Niki Hasrati <nhasrati@uwaterloo.ca> 1744744570 -0400	commit: Fixed bug with Vicuna
6ab20a489faa6b28284d3dec790f7b8a85842a4c 8fddca7943c72188b11abbbf312e8224b392cc95 Niki Hasrati <nhasrati@uwaterloo.ca> 1744753797 -0400	commit: Updated submodule
8fddca7943c72188b11abbbf312e8224b392cc95 a23b901a1d434abe41c78929b09935a893bbcaf3 Niki Hasrati <nhasrati@uwaterloo.ca> 1744753823 -0400	commit: Added util for loading activation chunks
a23b901a1d434abe41c78929b09935a893bbcaf3 0d9f7b362c996d3e37e222385af84125c484e099 Niki Hasrati <nhasrati@uwaterloo.ca> 1744818209 -0400	commit: Made activations code more efficient
0d9f7b362c996d3e37e222385af84125c484e099 b575be90d1266860e09e45b9d38b7596fdff1ee4 Niki Hasrati <nhasrati@uwaterloo.ca> 1744818839 -0400	commit: Updated submodule
b575be90d1266860e09e45b9d38b7596fdff1ee4 7cb51844262d7c4fcc6c811fcee6dbd1b9d364b9 Niki Hasrati <nhasrati@uwaterloo.ca> 1744819158 -0400	commit: Updated submodule
7cb51844262d7c4fcc6c811fcee6dbd1b9d364b9 5d6ba9a46122d7aec023b0481f5d336ac241655c Niki Hasrati <nhasrati@uwaterloo.ca> 1745675159 -0400	commit: Update readme and environment.yml
5d6ba9a46122d7aec023b0481f5d336ac241655c 1be1e6d21158e06ef9101ce0890a1d443fcaa2e2 Niki Hasrati <nhasrati@uwaterloo.ca> 1745675198 -0400	commit: Update config file
1be1e6d21158e06ef9101ce0890a1d443fcaa2e2 c300ee232d4bf8ba80b2d8c3af6e725ef79f4b7e Niki Hasrati <nhasrati@uwaterloo.ca> 1745675270 -0400	commit: Update code and scripts for generating and evaluating completions
c300ee232d4bf8ba80b2d8c3af6e725ef79f4b7e cf874961b15a9e62525e663debc0ddd278f3b87c Niki Hasrati <nhasrati@uwaterloo.ca> 1745675361 -0400	commit: Rename and move file
cf874961b15a9e62525e663debc0ddd278f3b87c ea9d05a04ffb3636b0923094361fcc54e5438da6 Niki Hasrati <nhasrati@uwaterloo.ca> 1745675464 -0400	commit: Add support for Llama 3 model
ea9d05a04ffb3636b0923094361fcc54e5438da6 617f31236cb40a8f2477df1b713783c6848da078 Niki Hasrati <nhasrati@uwaterloo.ca> 1745675548 -0400	commit: Update utils files
617f31236cb40a8f2477df1b713783c6848da078 f67f4cefc3894e3844a17453d68b925793163b55 Niki Hasrati <nhasrati@uwaterloo.ca> 1745676784 -0400	commit: Update submodule
f67f4cefc3894e3844a17453d68b925793163b55 3f6c9def35df9cdf4b63fb9011b10685faa9c814 Niki Hasrati <nhasrati@uwaterloo.ca> 1745679458 -0400	commit: add sparse_list files
3f6c9def35df9cdf4b63fb9011b10685faa9c814 9366bfeb8e3a6628c899a752bca08a13caccb681 Niki Hasrati <nhasrati@uwaterloo.ca> 1745680085 -0400	commit: Updated sparse_list.txt
9366bfeb8e3a6628c899a752bca08a13caccb681 9b2a096b2b12d6d2352762f81eef6c02a81edc96 Niki Hasrati <nhasrati@uwaterloo.ca> 1745681826 -0400	commit: Update sparse_list.txt
9b2a096b2b12d6d2352762f81eef6c02a81edc96 9a148059074b909cab646d8ddbb2db99e8022b53 Niki Hasrati <nhasrati@uwaterloo.ca> 1745682043 -0400	commit: Update sparse_list.txt
9a148059074b909cab646d8ddbb2db99e8022b53 0a8fd8669c8624c194007ffe69292343df6caab3 Niki Hasrati <nhasrati@uwaterloo.ca> 1745682630 -0400	commit: Update submodule_sparse_list.txt
0a8fd8669c8624c194007ffe69292343df6caab3 015fa85d6defdff25527d56e10130a595742333b Niki Hasrati <nhasrati@uwaterloo.ca> 1745685402 -0400	commit: Update evaluate_completions.sh script
015fa85d6defdff25527d56e10130a595742333b 3360707cc3cb17ebb43565e96c36f12192ae6742 Niki Hasrati <nhasrati@uwaterloo.ca> 1745685906 -0400	commit: Add setup.sh file
3360707cc3cb17ebb43565e96c36f12192ae6742 1895cf0c01b5f596ae031da566908c3c1f94df36 Niki Hasrati <nhasrati@uwaterloo.ca> 1745686037 -0400	commit: Update setup.sh
1895cf0c01b5f596ae031da566908c3c1f94df36 982302504c7c05225893e5f9a153d8897b0c5657 Niki Hasrati <nhasrati@uwaterloo.ca> 1745686216 -0400	commit: Update setup.sh
982302504c7c05225893e5f9a153d8897b0c5657 76b0c60c3394c6833bb7266d0944d436765a2199 Niki Hasrati <nhasrati@uwaterloo.ca> 1745687024 -0400	commit: Update setup.sh and evaluate_completions script
76b0c60c3394c6833bb7266d0944d436765a2199 9e9fce56843d306219576d082651b4bcea00f68f Niki Hasrati <nhasrati@uwaterloo.ca> 1745687611 -0400	commit: Update readme
9e9fce56843d306219576d082651b4bcea00f68f 103425a8432b716b2a72f1d630ca8bec270bab22 Niki Hasrati <nhasrati@uwaterloo.ca> 1745687756 -0400	commit: Update evaluate_completions script
103425a8432b716b2a72f1d630ca8bec270bab22 37aee5c3759c5ff29bec91178954ae3e69e68286 Niki Hasrati <nhasrati@uwaterloo.ca> 1745688259 -0400	commit: Update README
37aee5c3759c5ff29bec91178954ae3e69e68286 f155da29694d4f5773cb5c0e6b0e746a55226b8b Niki Hasrati <nhasrati@uwaterloo.ca> 1745688832 -0400	commit: Update README
f155da29694d4f5773cb5c0e6b0e746a55226b8b ebbe6d75f7ef772842e2c2fdd339eb7a3c0307f9 Niki Hasrati <nhasrati@uwaterloo.ca> 1746032953 -0400	commit: Remove submodule
ebbe6d75f7ef772842e2c2fdd339eb7a3c0307f9 dd3e10ebac1bd488350369ef44b7214426532510 Niki Hasrati <nhasrati@uwaterloo.ca> 1746033314 -0400	commit: Add code to save activations for Sarah
dd3e10ebac1bd488350369ef44b7214426532510 17ef62bc8799884a8049b389a5a0e308086ab93c Niki Hasrati <nhasrati@uwaterloo.ca> 1746037414 -0400	commit: Update config file
17ef62bc8799884a8049b389a5a0e308086ab93c a7f9b927d25367a1937e9b193eb482dbe03b5511 Niki Hasrati <nhasrati@uwaterloo.ca> 1746037854 -0400	commit: Update utils
a7f9b927d25367a1937e9b193eb482dbe03b5511 ce7499cd1e31cfa9c040175116a1c6ab1327f709 Niki Hasrati <nhasrati@uwaterloo.ca> 1746037962 -0400	commit: Update generate activations
ce7499cd1e31cfa9c040175116a1c6ab1327f709 33985f5ace8988ae47bb7c7ea2972a733af2fc99 Niki Hasrati <nhasrati@uwaterloo.ca> 1746058159 -0400	commit: Prepping for Alex and Avi to run jailbreak judge
33985f5ace8988ae47bb7c7ea2972a733af2fc99 338f2ae847fe64caaa6b21da7c2b51eb42ad4f6a Niki Hasrati <nhasrati@uwaterloo.ca> 1746115302 -0400	commit: Add flags for save_activations
338f2ae847fe64caaa6b21da7c2b51eb42ad4f6a e5863fc2cda51ff91468f148bd47443d3db1db69 Niki Hasrati <nhasrati@uwaterloo.ca> 1746116164 -0400	commit: Update env
e5863fc2cda51ff91468f148bd47443d3db1db69 604011cfd4d29090c6e66a72d375beec68579977 Niki Hasrati <nhasrati@uwaterloo.ca> 1746116784 -0400	commit: Update environment
604011cfd4d29090c6e66a72d375beec68579977 fa67dfb1b388f126ee66c17b2f3720a419335158 Niki Hasrati <nhasrati@uwaterloo.ca> 1746117065 -0400	commit: Update environment
fa67dfb1b388f126ee66c17b2f3720a419335158 8eb39afcc2ad640e85224fb290a73527a12d3d9c Niki Hasrati <nhasrati@uwaterloo.ca> 1746662270 -0400	commit: add phi files and setup files for Alex and Avi
8eb39afcc2ad640e85224fb290a73527a12d3d9c 71caeb1f7b62c3a01b0c4b3aeea22950a158615d Niki Hasrati <nhasrati@uwaterloo.ca> 1746803053 -0400	commit: Update setup files
71caeb1f7b62c3a01b0c4b3aeea22950a158615d 7009f2eef51459b33c93d7b9ce00f21ad92a7429 Niki Hasrati <nhasrati@uwaterloo.ca> 1746803172 -0400	commit: Fix
7009f2eef51459b33c93d7b9ce00f21ad92a7429 06960526b5b9c041b54aff011948a2c534f70410 Niki Hasrati <nhasrati@uwaterloo.ca> 1746803281 -0400	commit: Fix
06960526b5b9c041b54aff011948a2c534f70410 1170d518c51d718274d741c506aacf41380e4afb Niki Hasrati <nhasrati@uwaterloo.ca> 1746806004 -0400	commit: Update readme
1170d518c51d718274d741c506aacf41380e4afb eca841914afed13d5565be02fc47f9d28acde598 Niki Hasrati <nhasrati@uwaterloo.ca> 1746807347 -0400	commit: Update scripts
eca841914afed13d5565be02fc47f9d28acde598 a4601138c3f9d617f7d693548c5687364e0d6a1d Niki Hasrati <nhasrati@uwaterloo.ca> 1746814502 -0400	commit: Update files for Alex and Avi
a4601138c3f9d617f7d693548c5687364e0d6a1d 5e3efdddbd2379b59b8419717f06d11b8958d092 Niki Hasrati <nhasrati@uwaterloo.ca> 1746903690 -0400	commit: Update environment.yml file
5e3efdddbd2379b59b8419717f06d11b8958d092 ab8abc16f248e388310b50ea8dd371ff7502245f Niki Hasrati <nhasrati@uwaterloo.ca> 1746982082 -0400	commit: Add jailbreak judge script for Alex
ab8abc16f248e388310b50ea8dd371ff7502245f a18cbcd1dc572c1e90b01674436efc0e7f8f23fd Niki Hasrati <nhasrati@uwaterloo.ca> 1746985285 -0400	commit: Update script for Avi
