Chris Olah

Anthropic co-founder; leader of the mechanistic-interpretability program; previously Google Brain / Distill.

Role: founder
Currently at: Anthropic
Twitter: twitter.com/ch402
GitHub: github.com/colah
Scholar: scholar.google.com/citations
Papers: 2

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile: scholar.google.com/citations

Attribution policy →

2papers

Authored papers

Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

preprint

2022

Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

arXiv 2022

2022

Affiliations

Currently at

Anthropic

founder · frontier lab

Previously

Google Brainfrontier lab OpenAIfrontier lab

Frequent co-authors

from 2 papers

Amanda Askell

researcher

2 shared papers

Andy Jones

researcher

2 shared papers

Anna Chen

researcher

2 shared papers

Ben Mann

founder

2 shared papers

Catherine Olsson

researcher

2 shared papers

Danny Hernandez

researcher

2 shared papers

Dario Amodei

CEO

2 shared papers

Dawn Drain

researcher

2 shared papers

Deep Ganguli

researcher

2 shared papers

Jack Clark

founder

2 shared papers