9 citations · 30 across the 19 of their papers we have counts for
8 papers · 1 filter
Large Language Models Develop Belief State Geometry In-Context
Daniel Balcells, Andrew Jun Lee, Chirag Rastogi +3
Large language models (LLMs) trained on next-token prediction exhibit remarkable in-context learning (ICL) abilities, yet the representations that support ICL remain poorly underst…
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…
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…
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…
Better World Models Can Lead to Better Post-Training Performance
Prakhar Gupta, Henry Conklin, Sarah-Jane Leslie +1
We study how explicit world-modeling objectives affect the internal representations and downstream capability of Transformers, using Rubik's Cubes as our training domain. We ask: (…
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…