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

Developmental interpretability is a research agenda that has grown out of a meeting of the Singular Learning Theory (SLT) and AI alignment communitie…

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, for example...