collaborators

6 papers

cs.AI2026

LLMs Process Lists With General Filter Heads

Arnab Sen Sharma, Giordano Rogers, Natalie Shapira +1

We investigate the mechanisms underlying a range of list-processing tasks in LLMs, and we find that LLMs have learned to encode a compact, causal representation of a general filter…

cs.CL2026

Language Models use Lookbacks to Track Beliefs

Nikhil Prakash, Natalie Shapira, Arnab Sen Sharma +5

How do language models (LMs) represent characters' beliefs, especially when those beliefs may differ from reality? This question lies at the heart of understanding the Theory of Mi…

cs.CL2026

Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers

Adam Karvonen, James Chua, Clément Dumas +8

Large language model (LLM) activations are notoriously difficult to understand, with most existing techniques using complex, specialized methods for interpreting them. Recent work…

cs.LG2025

The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis

Aaron Mueller, Jannik Brinkmann, Millicent Li +10

Interpretability provides a toolset for understanding how and why neural networks behave in certain ways. However, there is little unity in the field: most studies employ ad-hoc ev…

cs.CL2025

Elucidating Mechanisms of Demographic Bias in LLMs for Healthcare

Hiba Ahsan, Arnab Sen Sharma, Silvio Amir +2

We know from prior work that LLMs encode social biases, and that this manifests in clinical tasks. In this work we adopt tools from mechanistic interpretability to unveil sociodemo…

cs.LG2025

NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals

Jaden Fiotto-Kaufman, Alexander R. Loftus, Eric Todd +17

We introduce NNsight and NDIF, technologies that work in tandem to enable scientific study of the representations and computations learned by very large neural networks. NNsight is…