A toolkit for describing model features and intervening on those features to steer behavior.
☆276Mar 16, 2026Updated 8 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:
- ☆150Nov 13, 2026Updated last week
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆283Updated this week
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆1,150Updated this week
- Code repo for the model organisms and convergent directions of EM papers.☆90Sep 22, 2025Updated last year
- ADAG: Transluce's MLP neuron-level circuit tracing library☆50Apr 10, 2026Updated 7 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Sparsify transformers with SAEs and transcoders☆744Updated this week
- A library for mechanistic interpretability of GPT-style language models☆4,086Updated this week
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated 2 years ago
- Training Sparse Autoencoders on Language Models☆1,588Updated this week
- A replication of Anthropic's Sleeper Agents and Stage-wise Model Diffing on a TinyStories language model.☆20Mar 17, 2025Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆68Oct 27, 2024Updated 2 years ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆59Oct 30, 2025Updated last year
- Mechanistic Interpretability Visualizations using React☆379Apr 30, 2026Updated 6 months ago
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆31Oct 11, 2026Updated last month
- 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.
- Unified access to Large Language Model modules using NNsight☆124Updated this week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆278Feb 27, 2026Updated 8 months ago
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆145Oct 7, 2026Updated last month
- A toolkit for embedding text datasets with sparse autoencoders☆32Mar 24, 2026Updated 7 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆95Nov 27, 2024Updated last year
- Teach LLMs to use NNSight with Skills☆15Updated this week
- MishformerLens intends to be a drop-in replacement for TransformerLens that AST patches HuggingFace Transformers rather than implementing…☆10Oct 7, 2024Updated 2 years ago
- Repository for "Training Language Models To Explain Their Own Computations"☆44Jul 7, 2026Updated 4 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆222Mar 12, 2026Updated 8 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.
- Attribution-based Parameter Decomposition☆35Jun 11, 2025Updated last year
- ☆29Sep 3, 2025Updated last year
- Open source interpretability artefacts for R1.☆187Apr 21, 2025Updated last year
- ☆20Apr 10, 2025Updated last year
- ☆226Oct 14, 2025Updated last year
- ☆38Nov 16, 2025Updated last year
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆34May 23, 2024Updated 2 years ago
- SAEs in Jax☆12Dec 16, 2024Updated last year
- ☆67Jul 4, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆610Jul 19, 2024Updated 2 years ago
- ☆19Updated this week
- A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.☆90Oct 25, 2026Updated 3 weeks ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆230Updated this week
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆920Mar 6, 2026Updated 8 months ago
- Official codebase for our paper "Do Language Models Use Their Depth Efficiently?"☆30Jun 25, 2025Updated last year
- Parameter Decomposition☆156Nov 6, 2026Updated 2 weeks ago
Are these results useful?