activity
20242026
most citedInto the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry

4 citations · 4 across the 3 of their papers we have counts for

collaborators

11 papers

cs.LG2026

From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?

Aaron Mueller, Andrew Lee, Shruti Joshi +3

A goal of interpretability is to recover disentangled representations of latent concepts (features) from the activations of neural networks. The quality of features is typically ev…

cs.LG2026

Tensor Product Representation Probes Reveal Shared Structure Across Linear Directions

Andrew Lee, Fernanda Viégas, Martin Wattenberg

While researchers are finding concepts represented as linear directions in language models, a bag of linear directions fails to capture relational structure. To better understand t…

cs.CV20264 cited

Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry

Thomas Fel, Binxu Wang, Michael A. Lepori +8

DINOv2 is routinely deployed to recognize objects, scenes, and actions; yet the nature of what it perceives remains unknown. As a working baseline, we adopt the Linear Representati…

cs.LG2026

Decomposing Query-Key Feature Interactions Using Contrastive Covariances

Andrew Lee, Yonatan Belinkov, Fernanda Viégas +1

Despite the central role of attention heads in Transformers, we lack tools to understand why a model attends to a particular token. To address this, we study the query-key (QK) spa…

cs.LG2025

Better World Models Can Lead to Better Post-Training Performance

Prakhar Gupta, Henry Conklin, Sarah-Jane Leslie +1

In this work we study how explicit world-modeling objectives affect the internal representations and downstream capability of Transformers across different training stages. We use…

cs.LG2025

Why Can't Transformers Learn Multiplication? Reverse-Engineering Reveals Long-Range Dependency Pitfalls

Xiaoyan Bai, Itamar Pres, Yuntian Deng +5

Language models are increasingly capable, yet still fail at a seemingly simple task of multi-digit multiplication. In this work, we study why, by reverse-engineering a model that s…