collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal

Leon Bergen, Usha Bhalla, Sidharth Baskaran +14

Language-model post-training is the main stage at which model behavior is shaped, yet it still largely involves optimization of scalar rewards that summarize diverse desiderata. Th…

cs.LG2026

Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior

Daniel Wurgaft, Can Rager, Matthew Kowal +13

Neural representations carry rich geometric structure; but does that structure causally shape behavior? To address this question, we intervene along paths through activation space…

cs.LG2026

Do Sparse Autoencoders Capture Concept Manifolds?

Usha Bhalla, Thomas Fel, Can Rager +9

Sparse autoencoders (SAEs) are widely used to extract interpretable features from neural network representations, often under the implicit assumption that concepts correspond to in…

cs.LG2025

MIB: A Mechanistic Interpretability Benchmark

Aaron Mueller, Atticus Geiger, Sarah Wiegreffe +20

How can we know whether new mechanistic interpretability methods achieve real improvements? In pursuit of lasting evaluation standards, we propose MIB, a Mechanistic Interpretabili…

cs.LG2025

How Do Transformers Learn Variable Binding in Symbolic Programs?

Yiwei Wu, Atticus Geiger, Raphaël Millière

Variable binding -- the ability to associate variables with values -- is fundamental to symbolic computation and cognition. Although classical architectures typically implement var…

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…