9 citations · 30 across the 19 of their papers we have counts for
8 papers · 1 filter
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: (…
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…
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…
Beyond Suboptimality: Resource-Rationality and Task Demands Shape the Complexity of Perceptual Representations
Andrew Jun Lee, Daniel Turek, Omer Daglar Tanrikulu
Early theories of perception as probabilistic inference propose that uncertainty about the interpretation of sensory input is represented as a probability distribution over many in…
The Geometry of Self-Verification in a Task-Specific Reasoning Model
Andrew Lee, Lihao Sun, Chris Wendler +2
How do reasoning models verify their own answers? We study this question by training a model using DeepSeek R1's recipe on the CountDown task. We leverage the fact that preference…
Shared Global and Local Geometry of Language Model Embeddings
Andrew Lee, Melanie Weber, Fernanda Viégas +1
Researchers have recently suggested that models share common representations. In our work, we find numerous geometric similarities across the token embeddings of large language mod…
ICLR: In-Context Learning of Representations
Core Francisco Park, Andrew Lee, Ekdeep Singh Lubana +5
Recent work has demonstrated that semantics specified by pretraining data influence how representations of different concepts are organized in a large language model (LLM). However…