Zero-code
- →Read the manifesto
- →Open a Discussion with a question or idea
- →Share a Trace you found interesting
- →Star the repos that helped you
OpenInterpretability is built in public by a growing group of students, researchers, and safety teams. Every notebook, every SAE, every line of site code can have your name on it.
Next.js site at openinterp.org — Trace Theater, Circuit Canvas, InterpScore leaderboard.
23+ training & interpretability notebooks, from 30-min Colab hobbyist to paper-grade cloud.
The openinterp Python package — SDK + CLI (pip install openinterp).
SAE features as dense RL rewards. Qwen3.5-4B → 64% → 83% on GSM8K.
If the change is > 20 lines, align first. Drafts welcome.
git checkout -b your-feature. Never push to main.
Local tests pass. Notebooks run start-to-finish.
Link to the issue. Paste numbers, screenshots, or logs.
A maintainer responds within 72h. We prefer kind + specific feedback.
4 repos, Apache-2.0 license, Discussions enabled on every repo. Star the ones you use.
OpenInterpretabilityDesign questions, cross-repo coordination, "which notebook should I run". Available on all 4 repos.
[email protected] — safety reports, partnership inquiries, Watchtower design partner.
We follow Contributor Covenant 2.1. Summary: be kind, be honest, assume good faith. Interpretability is a young field — many contributors are first-timers. Kindness is a feature, not a constraint. Report violations to [email protected].