Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.
☆200Mar 15, 2026Updated this week
Alternatives and similar repositories for Language-Model-SAEs
Users that are interested in Language-Model-SAEs are comparing it to the libraries listed below
Sorting:
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated last year
- Training Sparse Autoencoders on Language Models☆1,261Updated this week
- Open source replication of Anthropic's Crosscoders for Model Diffing☆63Oct 27, 2024Updated last year
- 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
- Sparsify transformers with SAEs and transcoders☆701Updated this week
- Applying SAEs for fine-grained control☆25Dec 15, 2024Updated last year
- ☆158Dec 30, 2025Updated 2 months ago
- ☆24Aug 23, 2025Updated 6 months ago
- ☆91Dec 18, 2025Updated 3 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆249Feb 27, 2026Updated 3 weeks ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆27Nov 20, 2024Updated last year
- ☆402Aug 21, 2025Updated 6 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆294Jul 20, 2024Updated last year
- ☆210Oct 14, 2025Updated 5 months ago
- ☆578Jul 19, 2024Updated last year
- A library for mechanistic interpretability of GPT-style language models☆3,183Mar 13, 2026Updated last week
- ☆58Nov 19, 2024Updated last year
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆13Jan 26, 2025Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆863Updated this week
- A tiny easily hackable implementation of a feature dashboard.☆16Oct 21, 2025Updated 4 months ago
- FeatureAlignment = Alignment + Mechanistic Interpretability☆34Mar 8, 2025Updated last year
- ☆104Aug 8, 2024Updated last year
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆76Jan 16, 2026Updated 2 months ago
- Open source interpretability artefacts for R1.☆173Apr 21, 2025Updated 10 months ago
- ☆24Jan 28, 2025Updated last year
- ☆28Nov 28, 2024Updated last year
- awesome SAE papers☆73May 24, 2025Updated 9 months ago
- Modified to support crosscoder training.☆25Feb 4, 2026Updated last month
- Information Extraction related tools and models☆10Mar 16, 2023Updated 3 years ago
- ☆20Apr 10, 2025Updated 11 months ago
- Mechanistic Interpretability Visualizations using React☆331Dec 18, 2024Updated last year
- A library for training crosscoders☆16May 28, 2025Updated 9 months ago
- [ICML'2024] Can AI Assistants Know What They Don't Know?☆85Feb 5, 2024Updated 2 years ago
- ☆15Aug 19, 2025Updated 7 months ago
- Using sparse coding to find distributed representations used by neural networks.☆298Nov 10, 2023Updated 2 years ago
- [NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".☆66Aug 15, 2025Updated 7 months ago
- Trains Sparse Autoencoders based on outputs from language models☆11Oct 7, 2024Updated last year
- Unified access to Large Language Model modules using NNsight☆102Feb 28, 2026Updated 2 weeks ago
- ☆75Jul 24, 2025Updated 7 months ago