decoderesearch / SAELensView external linksLinks
Training Sparse Autoencoders on Language Models
☆1,201Updated this week
Alternatives and similar repositories for SAELens
Users that are interested in SAELens are comparing it to the libraries listed below
Sorting:
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆240Dec 16, 2024Updated last year
- Sparsify transformers with SAEs and transcoders☆692Updated this week
- A library for mechanistic interpretability of GPT-style language models☆3,073Updated this week
- ☆389Aug 21, 2025Updated 5 months ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆811Updated this week
- Sparse Autoencoder for Mechanistic Interpretability☆291Jul 20, 2024Updated last year
- ☆146Dec 30, 2025Updated last month
- ☆570Jul 19, 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 …☆241Updated this week
- Mechanistic Interpretability Visualizations using React☆320Dec 18, 2024Updated last year
- ☆207Oct 14, 2025Updated 4 months ago
- ☆198Nov 17, 2024Updated last year
- Using sparse coding to find distributed representations used by neural networks.☆296Nov 10, 2023Updated 2 years ago
- ☆132Oct 28, 2023Updated 2 years ago
- Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.☆177Updated this week
- ☆88Dec 18, 2025Updated last month
- Sparse Autoencoder Training Library☆56May 1, 2025Updated 9 months ago
- ☆58Nov 19, 2024Updated last year
- ☆267Oct 1, 2024Updated last year
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆858Jan 29, 2026Updated 2 weeks ago
- ☆929Feb 4, 2026Updated last week
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆336Jul 23, 2025Updated 6 months ago
- Steering Llama 2 with Contrastive Activation Addition☆209May 23, 2024Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆567Aug 7, 2025Updated 6 months ago
- open source interpretability platform 🧠☆704Updated this week
- ☆153Sep 8, 2025Updated 5 months ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated last year
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆342Jun 13, 2025Updated 8 months ago
- Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)☆60Jul 24, 2025Updated 6 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆27Nov 20, 2024Updated last year
- ☆29Apr 4, 2024Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆64Oct 27, 2024Updated last year
- This repository collects all relevant resources about interpretability in LLMs☆387Nov 1, 2024Updated last year
- Representation Engineering: A Top-Down Approach to AI Transparency☆947Aug 14, 2024Updated last year
- ☆25Dec 20, 2023Updated 2 years ago
- Open source interpretability artefacts for R1.☆170Apr 21, 2025Updated 9 months ago
- ☆139Aug 4, 2024Updated last year
- Sparse probing paper full code.☆66Dec 17, 2023Updated 2 years ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆83Nov 27, 2024Updated last year