A toolkit for describing model features and intervening on those features to steer behavior.
☆232Mar 16, 2026Updated last week
Alternatives and similar repositories for observatory
Users that are interested in observatory are comparing it to the libraries listed below
Sorting:
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆863Updated this week
- Code repo for the model organisms and convergent directions of EM papers.☆56Sep 22, 2025Updated 5 months ago
- Sparsify transformers with SAEs and transcoders☆701Updated this week
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆245Updated this week
- MishformerLens intends to be a drop-in replacement for TransformerLens that AST patches HuggingFace Transformers rather than implementing…☆10Oct 7, 2024Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆175Mar 12, 2026Updated last week
- Repository for "Training Language Models To Explain Their Own Computations"☆21Dec 22, 2025Updated 2 months ago
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆29Feb 6, 2026Updated last month
- ☆87Updated this week
- A library for mechanistic interpretability of GPT-style language models☆3,183Mar 13, 2026Updated last week
- Open source interpretability artefacts for R1.☆173Apr 21, 2025Updated 11 months ago
- ☆210Oct 14, 2025Updated 5 months ago
- ☆29Nov 16, 2025Updated 4 months ago
- Attribution-based Parameter Decomposition☆34Jun 11, 2025Updated 9 months ago
- open source interpretability platform 🧠☆757Updated this week
- ☆403Aug 21, 2025Updated 7 months ago
- ☆19Sep 16, 2025Updated 6 months ago
- Official pytorch implementation of "Interpreting the Second-Order Effects of Neurons in CLIP"☆42Nov 15, 2024Updated last year
- ☆36Apr 30, 2024Updated last year
- ☆20Apr 10, 2025Updated 11 months ago
- Training Sparse Autoencoders on Language Models☆1,261Mar 14, 2026Updated last week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆251Feb 27, 2026Updated 3 weeks ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆84Nov 27, 2024Updated last year
- ☆83Feb 25, 2025Updated last year
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆77Jan 16, 2026Updated 2 months ago
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆868Mar 6, 2026Updated 2 weeks ago
- ☆39Jul 4, 2025Updated 8 months ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated last year
- ☆24Jan 27, 2026Updated last month
- ☆578Jul 19, 2024Updated last year
- ☆158Dec 30, 2025Updated 2 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆217Updated this week
- HypotheSAEs: hypothesizing interpretable relationships in text datasets using sparse autoencoders. https://arxiv.org/abs/2502.04382☆78Mar 8, 2026Updated 2 weeks ago
- ☆28Nov 28, 2024Updated last year
- [NeurIPS 2025 MechInterp Workshop - Spotlight] Official implementation of the paper "RelP: Faithful and Efficient Circuit Discovery in La…☆27Nov 3, 2025Updated 4 months ago
- Experiments in applying interpretability techniques to learned reward functions.☆10Dec 11, 2020Updated 5 years ago
- https://footprints.baulab.info☆18Oct 4, 2024Updated last year
- Interpreting Language Models with Contrastive Explanations (EMNLP 2022 Best Paper Honorable Mention)☆62May 12, 2022Updated 3 years ago
- Unified access to Large Language Model modules using NNsight☆103Feb 28, 2026Updated 3 weeks ago