Neuronpedia, an open source platform for AI interpretability

Neuronpedia, an open-source platform for AI interpretability, launched the world's first interpretability API in March 2024, enabling users to visualize, steer, and search over 50 million latents in AI models. Created by ex-Apple engineer Johnny Lin, the platform is supported by Anthropic, Open Philanthropy, and other organizations.

Visualize and trace the internal reasoning steps of a model with custom prompts, pioneered by Anthropic's circuit tracing papers. Steer Modify model behavior by steering its activations using latents or custom vectors. Steering supports instruct chat and reasoning models, and has fully customizable temperature, strength, seed, etc. Search Search over 50,000,000 latents/vectors, either by semantic similarity to explanation text, or by running custom text via inference through a model to find top matches. Search via Inference Run Example Search API + Libraries Neuronpedia hosts the world's first interpretability API March 2024 - and all functionality is available by API or Python/TypeScript libraries. Most endpoints have an OpenAPI spec and interactive docs. Inspect Go in depth on each probe/latent/feature with top activations, top logits, activation density, and live inference testing. All dashboards have unique links, can be compiled into sharable lists, and supports IFrame embedding, as demonstrated here. Who We Are Neuronpedia was created by Johnny Lin, an ex-Apple engineer who previously founded a privacy startup. Neuronpedia is supported by Decode Research, Open Philanthropy, the Long Term Future Fund, AISTOF, Anthropic, Manifund, and others.