ICML 2024 Workshop MI Submissions

Refusal in Language Models Is Mediated by a Single Direction
Andy Arditi, Oscar Balcells Obeso, Aaquib Syed, Daniel Paleka, Nina Panickssery, Wes Gurnee, Neel Nanda
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Poster
- Readers: Everyone
Automatically Identifying Local and Global Circuits with Linear Computation Graphs
Xuyang Ge, Fukang Zhu, Wentao Shu, Junxuan Wang, Zhengfu He, Xipeng Qiu
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Poster
- Readers: Everyone
Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller
Min Cai, Yuchen Zhang, Shichang Zhang, Fan Yin, Difan Zou, Yisong Yue, Ziniu Hu
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Poster
- Readers: Everyone
Segmentation CNNs are denoising models
Luis A. Zavala-Mondragón, Ruud Van Sloun, Peter H.N. de With, Fons van der Sommen
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Poster
- Readers: Everyone
Delay Embedding Theory of Neural Sequence Models
Mitchell Ostrow, Adam Joseph Eisen, Ila R Fiete
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Poster
- Readers: Everyone
On the Similarity of Circuits across Languages: a Case Study on the Subject-verb Agreement Task
Javier Ferrando, Marta R. Costa-jussà
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Poster
- Readers: Everyone
Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP
Sriram Balasubramanian, Samyadeep Basu, Soheil Feizi
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Spotlight
- Readers: Everyone
The Geometry of Categorical and Hierarchical Concepts in Large Language Models
Kiho Park, Yo Joong Choe, Yibo Jiang, Victor Veitch
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Oral
- Readers: Everyone
Adversarial Circuit Evaluation
Niels uit de Bos, Adrià Garriga-Alonso
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Poster
- Readers: Everyone
What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
Samyak Jain, Ekdeep Singh Lubana, Kemal Oksuz, Tom Joy, Philip Torr, Amartya Sanyal, Puneet K. Dokania
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Spotlight
- Readers: Everyone
Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization
Boshi Wang, Xiang Yue, Yu Su, Huan Sun
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Spotlight
- Readers: Everyone
Investigating the Indirect Object Identification circuit in Mamba
Danielle Ensign, Adrià Garriga-Alonso
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Poster
- Readers: Everyone
Logical Distillation of Graph Neural Networks
Alexander Pluska, Pascal Welke, Thomas Gärtner, SAGAR MALHOTRA
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Poster
- Readers: Everyone
Benchmarking Mental State Representations in Language Models
Matteo Bortoletto, Constantin Ruhdorfer, Lei Shi, Andreas Bulling
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Poster
- Readers: Everyone
Look Before You Leap: A Universal Emergent Decomposition of Retrieval Tasks in Language Models
Alexandre Variengien, Eric Winsor
- Published: 24 Jun 2024, Last Modified: 24 Jun 2024
- ICML 2024 MI Workshop Spotlight
- Readers: Everyone
Contrastive Sparse Autoencoders for Interpreting Planning of Chess-Playing Agents
Yoann Poupart
- Published: 24 Jun 2024, Last Modified: 24 Jun 2024
- ICML 2024 MI Workshop Poster
- Readers: Everyone
Describe-and-Dissect: Interpreting Neurons in Vision Networks with Language Models
Nicholas Bai, Rahul Ajay Iyer, Tuomas Oikarinen, Tsui-Wei Weng
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Spotlight
- Readers: Everyone
How do Llamas process multilingual text? A latent exploration through activation patching
Clément Dumas, Veniamin Veselovsky, Giovanni Monea, Robert West, Chris Wendler
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Spotlight
- Readers: Everyone
Iteration Head: A Mechanistic Study of Chain-of-Thought
Vivien Cabannes, Charles Arnal, Wassim Bouaziz, Xingyu Alice Yang, Francois Charton, Julia Kempe
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Poster
- Readers: Everyone
Hypothesis Testing the Circuit Hypothesis in LLMs
Claudia Shi, Nicolas Beltran-Velez, Achille Nazaret, Carolina Zheng, Adrià Garriga-Alonso, Andrew Jesson, Maggie Makar, David Blei
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Oral
- Readers: Everyone
Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks
Tianyu He, Darshil Doshi, Aritra Das, Andrey Gromov
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Spotlight
- Readers: Everyone
Mathematical Models of Computation in Superposition
Kaarel Hänni, Jake Mendel, Dmitry Vaintrob, Lawrence Chan
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Poster
- Readers: Everyone
Transcoders find interpretable LLM feature circuits
Jacob Dunefsky, Philippe Chlenski, Neel Nanda
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Spotlight
- Readers: Everyone
TracrBench: Generating Interpretability Testbeds with Large Language Models
Hannes Thurnherr, Jérémy Scheurer
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Poster
- Readers: Everyone
Uncovering Latent Memories: Assessing Data Leakage and Memorization Patterns in Large Language Models
Sunny Duan, Mikail Khona, Abhiram Iyer, Rylan Schaeffer, Ila R Fiete
- Published: 24 Jun 2024, Last Modified: 31 Jul 2024
- ICML 2024 MI Workshop Poster
- Readers: Everyone