Company name
2022Founder
Chris Olah leads interpretability research at Anthropic, studying the internal mechanisms of neural networks. He previously worked on interpretability at OpenAI and developed neural-network visualization methods at Google Brain; his writing and research have helped make these techniques accessible, including through Distill, the journal he co-founded.
Co-founder and Interpretability Research Lead
Co-founded Anthropic and leads research focused on understanding the internal mechanisms of neural networks.
Interpretability researcher
Worked on neural-network interpretability through OpenAI's Clarity research team. In a 2020 essay co-authored with OpenAI colleagues, he and the team analyzed how curve-detecting features are implemented and tested, including through synthetic inputs and circuit-level evidence.
Research Scientist
Conducted research on neural networks, visualization, interpretability, and AI safety.
Developer, Adaptations and Imapcts Research Division
Developer, Department of Forestry