A toolkit for describing model features and intervening on those features to steer behavior.
☆267Mar 16, 2026Updated 6 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:
- ☆139Updated this week
- Code repo for the model organisms and convergent directions of EM papers.☆86Sep 22, 2025Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆1,122Updated this week
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆279Updated this week
- ADAG: Transluce's MLP neuron-level circuit tracing library☆41Apr 10, 2026Updated 6 months ago
- 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.
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆30Feb 6, 2026Updated 8 months ago
- Sparsify transformers with SAEs and transcoders☆742Updated this week
- A library for mechanistic interpretability of GPT-style language models☆3,959Updated this week
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆58Oct 30, 2025Updated 11 months ago
- ☆65Jul 4, 2025Updated last year
- Training Sparse Autoencoders on Language Models☆1,552Oct 4, 2026Updated last week
- Open source interpretability artefacts for R1.☆184Apr 21, 2025Updated last year
- Repository for "Training Language Models To Explain Their Own Computations"☆38Jul 7, 2026Updated 3 months ago
- MishformerLens intends to be a drop-in replacement for TransformerLens that AST patches HuggingFace Transformers rather than implementing…☆10Oct 7, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆218Mar 12, 2026Updated 6 months ago
- Unified access to Large Language Model modules using NNsight☆121Updated this week
- ☆37Nov 16, 2025Updated 10 months ago
- Mechanistic Interpretability Visualizations using React☆368Apr 30, 2026Updated 5 months ago
- ☆18Sep 18, 2026Updated 3 weeks ago
- A toolkit for embedding text datasets with sparse autoencoders☆32Mar 24, 2026Updated 6 months ago
- Attribution-based Parameter Decomposition☆35Jun 11, 2025Updated last year
- ☆225Oct 14, 2025Updated 11 months ago
- ☆20Apr 10, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Official codebase for our paper "Do Language Models Use Their Depth Efficiently?"☆29Jun 25, 2025Updated last year
- ☆30Aug 2, 2024Updated 2 years ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆225Sep 28, 2026Updated last week
- ☆41Jul 9, 2025Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆276Feb 27, 2026Updated 7 months ago
- Benchmarking Dark Patterns in LLMs (ICLR 2025)☆19Mar 29, 2025Updated last year
- ☆430Aug 21, 2025Updated last year
- ☆29Sep 3, 2025Updated last year
- ☆88Feb 25, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆905Mar 6, 2026Updated 7 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆94Nov 27, 2024Updated last year
- ☆1,345Updated this week
- ☆150Aug 4, 2024Updated 2 years ago
- open source interpretability platform 🧠☆1,163Updated this week
- ☆213Nov 17, 2024Updated last year
- Parameter Decomposition☆149Updated this week