24 citations · 24 across the 14 of their papers we have counts for
15 papers
Language Model Activations Inhabit Privileged Error-Correcting Basins
Matthew Finlayson, Francisco Pernice, Eric Todd +16
Language models exhibit remarkable robustness, continuing to produce coherent text even when their activations are perturbed by interventions like linear steering. We hypothesize t…
auto-psych: Automating the science of mind using agent-driven theory discovery and experimentation
Ben Prystawski, Kushin Mukherjee, Daniel Wurgaft +4
AI-based scientific automation is increasingly possible by using agents to generate hypotheses, design experiments, and analyze data. Data collection is a major bottleneck in this…
Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds
Thomas Fel, Matthew Kowal, Mozes Jacobs +22
What is the geometry of a visual percept? The most widely used protocols for decomposing neural network representations into interpretable parts treat concepts as isolated directio…
Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention
Jing Huang, Daniel Wurgaft, Rachit Bansal +6
Larger models learn tasks smaller models do not. What drives this phenomenon? We develop a simple phenomenological argument that power-law scaling already suggests that a larger mo…
Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space
Eric Bigelow, Raphaël Sarfati, Daniel Wurgaft +5
Large Language Models (LLMs) update their behavior in context, which can be viewed as a form of Bayesian inference. However, the structure of the latent hypothesis space over which…
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…
Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts
Sheridan Feucht, Tal Haklay, Usha Bhalla +9
Does structure in representations imply structure in computation? We study how Llama-3.1-8B reasons over cyclic concepts (e.g., "what month is six months after August?"). Even thou…
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…
The Shape of Beliefs: Geometry, Dynamics, and Interventions along Representation Manifolds of Language Models' Posteriors
Raphaël Sarfati, Eric Bigelow, Daniel Wurgaft +6
Large language models (LLMs) form implicit beliefs (posteriors over latent variables) from prompts, but we lack a mechanistic account of how these beliefs are encoded in representa…
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…
Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering
Eric Bigelow, Daniel Wurgaft, YingQiao Wang +4
Large language models (LLMs) can be controlled at inference time through prompts (in-context learning) and internal activations (activation steering). Different accounts have been…
Diagnosing Bottlenecks in Data Visualization Understanding by Vision-Language Models
Alexa R. Tartaglini, Satchel Grant, Daniel Wurgaft +2
Data visualizations are vital components of many scientific articles and news stories. Current vision-language models (VLMs) still struggle on basic data visualization understandin…
In-Context Learning Strategies Emerge Rationally
Daniel Wurgaft, Ekdeep Singh Lubana, Core Francisco Park +3
Recent work analyzing in-context learning (ICL) has identified a broad set of strategies that describe model behavior in different experimental conditions. We aim to unify these fi…
Scaling up the think-aloud method
Daniel Wurgaft, Ben Prystawski, Kanishk Gandhi +3
The think-aloud method, where participants voice their thoughts as they solve a task, is a valuable source of rich data about human reasoning processes. Yet, it has declined in pop…
Inverse Scaling: When Bigger Isn't Better
Ian R. McKenzie, Alexander Lyzhov, Michael Pieler +24
Work on scaling laws has found that large language models (LMs) show predictable improvements to overall loss with increased scale (model size, training data, and compute). Here, w…