Chris Olah
Also known as Christopher Olah
Canadian interpretability researcher; Anthropic co-founder, earlier at OpenAI and Google Brain.
At a glance
Also on this page: Key facts · Links · Sources · Related pages
- Chris Olah is a Canadian machine learning researcher known for work on neural network interpretability, especially mechanistic interpretability.
- He started at Google Brain in 2015, co-founded the journal Distill in 2017, led OpenAI's interpretability team from 2018 to 2020 and co-founded Anthropic, where he leads interpretability research.
- His blog explains how neural networks work, and Time put him on its TIME100 AI list in 2024.
Key facts
- Role
- Co-founder of Anthropic; interpretability research1
- Earlier
- Google Brain, from intern to research scientist, from 2015 to 2018; led OpenAI's interpretability team from 2018 to 20201
- Also
- Co-founded Distill, an interactive machine learning journal (2017)1
- Recognition
- Thiel Fellowship (2012); TIME100 AI (2024)1
- Blog
- colah's blog: illustrated essays such as Understanding LSTM Networks2
Roles
Founded
Before
Part of until 2018
Google (Google Brain, from intern to research scientist) source on Google
Part of until 2020
OpenAI (led the interpretability team) source on OpenAI
Links
Sources
Last checked against its sources today
Is something on this page wrong or out of date? Tell us
How recent
The line under a date fills as time passes: empty when new, then one equal share each for a day, a week, a month and a year. For episodes and other items it is full at 2 years; for "last checked", at a year. A striped line means the date is known only to the month or year.