Chris Olah
Co-founder, Anthropic; interpretability research lead
Chris Olah is a machine learning researcher and co-founder of Anthropic, where he leads interpretability research into how AI models work internally. He previously led OpenAI's interpretability team from 2018 to 2020 and worked at Google Brain, and co-founded the journal Distill.
In the library
Nothing of theirs is filed in the hub yet. Browse the full library.
Recommended next
Hand-picked from the hub based on what Chris Olah covers.
Emotion concepts in a large language model
Anthropic interpretability research looking at internal representations that behave like emotions in its Claude model.
Why this: Covers Anthropic and interpretability too
Claude Fable and Mythos 5.2: System Card & Safety Evaluation Breakdown
In-depth analysis of Anthropic's Claude Fable 5.2 and Mythos 5.2 system card, capability jumps, cyber-defense evaluations, and alignment stress-testing.
Why this: Covers Anthropic and AI safety too
Investigating Unintended Model Actions in Evaluations and Internal Use
A research write-up from Anthropic describing instances of unintended behavior observed in model evaluations and internal usage, and the methods used to investigate and address them.
Why this: Covers Anthropic and AI safety too
Expanding the Cyber Verification Program
An announcement from Anthropic describing an expanded version of its Cyber Verification Program, which gives qualifying security professionals access to advanced cyber capabilities and reduced blocking classifiers in its models.
Why this: Covers Anthropic and AI safety too