A toolkit for describing model features and intervening on those features to steer behavior.
☆240Mar 16, 2026Updated 2 months ago
Alternatives and similar repositories for observatory
Users that are interested in observatory are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆948Jun 2, 2026Updated last week
- Sparsify transformers with SAEs and transcoders☆725Updated this week
- Code repo for the model organisms and convergent directions of EM papers.☆69Sep 22, 2025Updated 8 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆258Jun 1, 2026Updated last week
- MishformerLens intends to be a drop-in replacement for TransformerLens that AST patches HuggingFace Transformers rather than implementing…☆10Oct 7, 2024Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆195Mar 12, 2026Updated 2 months ago
- Repository for "Training Language Models To Explain Their Own Computations"☆22Dec 22, 2025Updated 5 months ago
- ☆41Dec 7, 2025Updated 6 months ago
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆30Feb 6, 2026Updated 4 months ago
- Open source interpretability artefacts for R1.☆177Apr 21, 2025Updated last year
- A library for mechanistic interpretability of GPT-style language models☆3,526Updated this week
- ☆217Oct 14, 2025Updated 7 months ago
- ☆108Updated this week
- Attribution-based Parameter Decomposition☆34Jun 11, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆33Nov 16, 2025Updated 6 months ago
- ☆168May 1, 2026Updated last month
- ☆49May 17, 2026Updated 3 weeks ago
- open source interpretability platform 🧠☆908Updated this week
- ☆419Aug 21, 2025Updated 9 months ago
- ☆20Apr 26, 2026Updated last month
- ☆19Apr 10, 2025Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆261Feb 27, 2026Updated 3 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆87Nov 27, 2024Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Training Sparse Autoencoders on Language Models☆1,414Updated this week
- ☆38Apr 30, 2024Updated 2 years ago
- ☆83Feb 25, 2025Updated last year
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆81Jan 16, 2026Updated 4 months ago
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆883Mar 6, 2026Updated 3 months ago
- ☆30Aug 2, 2024Updated last year
- ☆46Jul 4, 2025Updated 11 months ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated last year
- ☆25Apr 1, 2026Updated 2 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- ☆589Jul 19, 2024Updated last year
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆220Jun 1, 2026Updated last week
- ☆31Nov 28, 2024Updated last year
- HypotheSAEs: hypothesizing interpretable relationships in text datasets using sparse autoencoders. https://arxiv.org/abs/2502.04382☆88May 25, 2026Updated 2 weeks ago
- ☆107May 23, 2026Updated 2 weeks ago
- [NeurIPS 2025 MechInterp Workshop - Spotlight] Official implementation of the paper "RelP: Faithful and Efficient Circuit Discovery in La…☆29Nov 3, 2025Updated 7 months ago
- Experiments in applying interpretability techniques to learned reward functions.☆10Dec 11, 2020Updated 5 years ago