Dr. Sarah Williams

Machine Learning Researcher

Cambridge, MA

I study how machines learn to reason about language.

Assistant Professor at MIT CSAIL. My research focuses on
interpretability and alignment in large language models.

Previously: Research Scientist at DeepMind, PhD at Stanford.

Selected Works

View Complete Collection →

Experiments

Attention Atlas

Interactive web visualization of attention patterns across transformer layers and heads.

Synthetic Language Generator

Tool for creating controlled synthetic languages to test compositional generalization.

Chain-of-Thought Analyzer

Scripts for analyzing and categorizing chain-of-thought reasoning patterns in LLM outputs.

View All Experiments →

Publications

View All Publications →