A toolkit for describing model features and intervening on those features to steer behavior.
☆244Mar 16, 2026Updated 3 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.☆971Updated this week
- Sparsify transformers with SAEs and transcoders☆729Jun 22, 2026Updated last week
- Code repo for the model organisms and convergent directions of EM papers.☆70Sep 22, 2025Updated 9 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆262Updated this week
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆203Mar 12, 2026Updated 3 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Repository for "Training Language Models To Explain Their Own Computations"☆22Dec 22, 2025Updated 6 months ago
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆30Feb 6, 2026Updated 4 months ago
- Open source interpretability artefacts for R1.☆183Apr 21, 2025Updated last year
- A library for mechanistic interpretability of GPT-style language models☆3,603Updated this week
- ☆219Oct 14, 2025Updated 8 months ago
- ☆111Updated this week
- Attribution-based Parameter Decomposition☆35Jun 11, 2025Updated last year
- ☆34Nov 16, 2025Updated 7 months ago
- ☆174May 1, 2026Updated 2 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- open source interpretability platform 🧠☆932Jun 17, 2026Updated 2 weeks ago
- ☆424Aug 21, 2025Updated 10 months ago
- ☆19Apr 10, 2025Updated last year
- Official pytorch implementation of "Interpreting the Second-Order Effects of Neurons in CLIP"☆42Nov 15, 2024Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆262Feb 27, 2026Updated 4 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆87Nov 27, 2024Updated last year
- Training Sparse Autoencoders on Language Models☆1,442Jun 24, 2026Updated last week
- ☆38Apr 30, 2024Updated 2 years ago
- ☆84Feb 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.
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆81Jun 20, 2026Updated last week
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆888Mar 6, 2026Updated 3 months ago
- ☆30Aug 2, 2024Updated last year
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated last year
- ☆27Apr 1, 2026Updated 3 months ago
- ☆49Jul 4, 2025Updated 11 months ago
- ☆590Jul 19, 2024Updated last year
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆220Jun 22, 2026Updated last week
- ☆32Nov 28, 2024Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- HypotheSAEs: hypothesizing interpretable relationships in text datasets using sparse autoencoders. https://arxiv.org/abs/2502.04382☆90May 25, 2026Updated last month
- ☆107May 23, 2026Updated last month
- [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
- Interpreting Language Models with Contrastive Explanations (EMNLP 2022 Best Paper Honorable Mention)☆63May 12, 2022Updated 4 years ago
- Code for steering and monitoring with concepts vectors in LLMs (initial draft)☆31Aug 10, 2025Updated 10 months ago
- Mechanistic Interpretability Visualizations using React☆352Apr 30, 2026Updated 2 months ago