papers

Publications (7)

cs.CL2026

In-Context Algebra

Eric Todd, Jannik Brinkmann, Rohit Gandikota +1

We investigate the mechanisms that arise when transformers are trained to solve arithmetic on sequences where tokens are variables whose meaning is determined only through their in…

cs.LG2025

Open Problems in Mechanistic Interpretability

Lee Sharkey, Bilal Chughtai, Joshua Batson +26

Mechanistic interpretability aims to understand the computational mechanisms underlying neural networks' capabilities in order to accomplish concrete scientific and engineering goa…

cs.CL2026

Shared Lexical Task Representations Explain Behavioral Variability In LLMs

Zhuonan Yang, Jacob Xiaochen Li, Francisco Piedrahita Velez +5

One of the most common complaints about large language models (LLMs) is their prompt sensitivity -- that is, the fact that their ability to perform a task or provide a correct answ…

cs.CL2024

Function Vectors in Large Language Models

Eric Todd, Millicent L. Li, Arnab Sen Sharma +3

We report the presence of a simple neural mechanism that represents an input-output function as a vector within autoregressive transformer language models (LMs). Using causal media…

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

The Dual-Route Model of Induction

Sheridan Feucht, Eric Todd, Byron Wallace +1

Prior work on in-context copying has shown the existence of induction heads, which attend to and promote individual tokens during copying. In this work we discover a new type of in…

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…