OpenReview
.net
OpenReview
.net
Login
OpenReview
.net
Login
Jack Merullo
Researcher, Goodfire
Joined
November 2021
Names
Jack Merullo
(Preferred)
,
jack merullo
Emails
****@brown.edu
(Confirmed)
,
****@goodfire.ai
(Confirmed)
Personal Links
Homepage
Google Scholar
DBLP
Semantic Scholar
ACL Anthology
Career & Education History
Researcher
Goodfire
(goodfire.ai)
2025
–
Present
PhD student
Computer Science,
Brown University
(brown.edu)
2020
–
2025
Undergrad student
University of Massachusetts at Amherst
(umass.edu)
2016
–
2020
Advisors, Relations & Conflicts
PhD Advisor
Carsten Eickhoff
2020
–
2025
PhD Advisor
Ellie Pavlick
2020
–
2025
Expertise
interpretability
2022
–
Present
representation learning
2020
–
Present
grounded language
,
grounding
,
multimodal
,
language understanding
,
interpretability
2020
–
Present
Publications
Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
Daniel Wurgaft
,
Can Rager
,
Matthew Kowal
,
Vasudev Shyam
,
Sheridan Feucht
,
Usha Bhalla
,
Tal Haklay
,
Eric Bigelow
,
Raphaël Sarfati
,
Thomas McGrath
,
Owen Lewis
,
Jack Merullo
,
Noah Goodman
,
Thomas Fel
,
Atticus Geiger
,
Ekdeep Singh Lubana
Mech Interp Workshop ICML 2026 Spotlight
Readers:
Everyone
Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts
Sheridan Feucht
,
Tal Haklay
,
Usha Bhalla
,
Daniel Wurgaft
,
Can Rager
,
Jack Merullo
,
Thomas McGrath
,
Raphaël Sarfati
,
Owen Lewis
,
Ekdeep Singh Lubana
,
Thomas Fel
,
Atticus Geiger
Mech Interp Workshop ICML 2026 Poster
Readers:
Everyone
From Memorization to Reasoning in the Spectrum of Loss Curvature
Jack Merullo
,
Srihita Vatsavaya
,
Lucius Bushnaq
,
Owen Lewis
Submitted to ICLR 2026
Readers:
Everyone
Shared Memorization Structures in Transformers Revealed by Loss Curvature
Jack Merullo
,
Srihita Vatsavaya
,
Owen Lewis
Mech Interp Workshop (NeurIPS 2025) Poster
Readers:
Everyone
I Have No Mouth, and I Must Rhyme: Uncovering Internal Phonetic Representations in LLaMA 3.2
Oliver McLaughlin
,
Jack Merullo
,
Arjun Khurana
ICML 2025 World Models Workshop
Readers:
Everyone
Transferring Linear Features Across Language Models With Model Stitching
Alan Chen
,
Jack Merullo
,
Alessandro Stolfo
,
Ellie Pavlick
NeurIPS 2025 spotlight
Readers:
Everyone
$100K or 100 Days: Trade-offs when Pre-Training with Academic Resources
Apoorv Khandelwal
,
Tian Yun
,
Nihal V. Nayak
,
Jack Merullo
,
Stephen Bach
,
Chen Sun
,
Ellie Pavlick
COLM 2025
Readers:
Everyone
On Linear Representations and Pretraining Data Frequency in Language Models
Jack Merullo
,
Noah A. Smith
,
Sarah Wiegreffe
,
Yanai Elazar
ICLR 2025 Poster
Readers:
Everyone
Transformer Mechanisms Mimic Frontostriatal Gating Operations When Trained on Human Working Memory Tasks
Aneri Soni
,
Aaron Traylor
,
Jack Merullo
,
Michael Frank
,
Ellie Pavlick
Submitted to ICLR 2025
Readers:
Everyone
Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting
Suraj Anand
,
Michael A. Lepori
,
Jack Merullo
,
Ellie Pavlick
ICLR 2025 Poster
Readers:
Everyone
View all 28 publications
Co-Authors
Aaron Traylor
Abram Handler
Alan Chen
Alessandro Stolfo
Alvin Grissom II
Aneri Soni
Ankita Gupta
Apoorv Khandelwal
Arjun Khurana
Atticus Geiger
Brendan O'Connor
Can Rager
Carsten Eickhoff
Chen Sun
Daniel Wurgaft
Dylan Ebert
Ekdeep Singh Lubana
Ellie Pavlick
Eric Bigelow
Kalpesh Krishna
Laura Mercurio
Louis Castricato
Lucius Bushnaq
Luke Yeh
Martha Lewis
View all 51 co-authors