activity
20242026
most citedAgents of Chaos

6 citations · 6 across the 3 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2025

Priors in Time: Missing Inductive Biases for Language Model Interpretability

Ekdeep Singh Lubana, Can Rager, Sai Sumedh R. Hindupur +13

Recovering meaningful concepts from language model activations is a central aim of interpretability. While existing feature extraction methods aim to identify concepts that are ind…

cs.LG2025

Automatically Finding Rule-Based Neurons in OthelloGPT

Aditya Singh, Zihang Wen, Srujananjali Medicherla +2

OthelloGPT, a transformer trained to predict valid moves in Othello, provides an ideal testbed for interpretability research. The model is complex enough to exhibit rich computatio…

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.LG2025

SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Adam Karvonen, Can Rager, Johnny Lin +12

Sparse autoencoders (SAEs) are a popular technique for interpreting language model activations, and there is extensive recent work on improving SAE effectiveness. However, most pri…

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…

cs.LG2025

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

Samuel Marks, Can Rager, Eric J. Michaud +3

We introduce methods for discovering and applying sparse feature circuits. These are causally implicated subnetworks of human-interpretable features for explaining language model b…