Skip to main content

Awesome tools for interpreting, manipulating the internals of of deep neural networks.

10
GitHub Stars
57
Curated Resources
4
Categories
23 hours ago
Last Refreshed
Mechanistic interpretability librariesExplainability, counterfactuals and probingStructured outputSee more

Use this list with your AI agent

Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:

"Show me explainability, counterfactuals and probing resources from awesome-interpretability"

Installation instructions →

What's inside

Showing a sample of 57 resources. View the full list on GitHub →