← Back to Directory
Chris Olah

Chris Olah

Builder

San Francisco

@colah

Co-founder of Anthropic's interpretability team. Pioneer of neural network visualization and mechanistic interpretability research.

Skills

interpretabilityneural networksvisualizationresearchpython

Looking For

collaborator

Research Foundations (2)

Attention Is All You Need

NeurIPS 201720176,510 citations

Used by: Circuits / Mechanistic Interpretability

Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

ICML 201620168,200 citations

Used by: Circuits / Mechanistic Interpretability

Projects (1)

Circuits / Mechanistic Interpretability

Live

Pioneering research on understanding neural networks by reverse-engineering their internal mechanisms. Published the influential Circuits thread on Distill.

Generative AIAI Safety

Built on research:

paperAttention Is All You Need(2017)
paperDropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning(2016)

AI Suggested Researchers

Researchers whose work may be relevant to your projects (auto-detected)

Yoshua Bengio

Yoshua Bengio

Mila / Université de Montréal

Shared domains: Generative AI, AI Safety
67% matchAI suggested
Ilya Sutskever

Ilya Sutskever

Safe Superintelligence Inc.

Shared domains: Generative AI, AI Safety
67% matchAI suggested
Ian Goodfellow

Ian Goodfellow

Google DeepMind

Shared domains: Generative AI, AI Safety
60% matchAI suggested
Shakir Mohamed

Shakir Mohamed

Google DeepMind

Shared domains: Generative AI, AI Safety
60% matchAI suggested

AI Suggested Papers

Papers that may have inspired your projects (auto-detected by domain & keyword analysis)

WebsiteTwitterGitHub