activity
20242026
collaborators

7 papers

cs.LG2026

Structural Inference: Interpreting Small Language Models with Susceptibilities

Garrett Baker, George Wang, Jesse Hoogland +1

We develop a linear response framework for interpretability that treats a neural network as a Bayesian statistical mechanical system. A small perturbation of the data distribution,…

cs.LG2026

Patterning: The Dual of Interpretability

George Wang, Daniel Murfet

Mechanistic interpretability aims to understand how neural networks generalize beyond their training data by reverse-engineering their internal structures. We introduce patterning…

cs.LG2026

Towards Spectroscopy: Susceptibility Clusters in Language Models

Andrew Gordon, Garrett Baker, George Wang +3

Spectroscopy infers the internal structure of physical systems by measuring their response to perturbations. We apply this principle to neural networks: perturbing the data distrib…

cs.LG2025

Embryology of a Language Model

George Wang, Garrett Baker, Andrew Gordon +1

Understanding how language models develop their internal computational structure is a central problem in the science of deep learning. While susceptibilities, drawn from statistica…

cs.LG2025

Loss Landscape Degeneracy and Stagewise Development in Transformers

Jesse Hoogland, George Wang, Matthew Farrugia-Roberts +3

Deep learning involves navigating a high-dimensional loss landscape over the neural network parameter space. Over the course of training, complex computational structures form and…

cs.LG2025

You Are What You Eat -- AI Alignment Requires Understanding How Data Shapes Structure and Generalisation

Simon Pepin Lehalleur, Jesse Hoogland, Matthew Farrugia-Roberts +5

In this position paper, we argue that understanding the relation between structure in the data distribution and structure in trained models is central to AI alignment. First, we di…