Training Sparse Autoencoders on Language Models
☆1,389May 20, 2026Updated this week
Alternatives and similar repositories for SAELens
Users that are interested in SAELens are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Sparsify transformers with SAEs and transcoders☆721Updated this week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆259Feb 27, 2026Updated 3 months ago
- A library for mechanistic interpretability of GPT-style language models☆3,461Updated this week
- ☆416Aug 21, 2025Updated 9 months ago
- ☆166May 1, 2026Updated 3 weeks ago
- 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.
- Sparse Autoencoder for Mechanistic Interpretability☆297Jul 20, 2024Updated last year
- ☆588Jul 19, 2024Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆936Updated this week
- Mechanistic Interpretability Visualizations using React☆348Apr 30, 2026Updated 3 weeks ago
- ☆214Oct 14, 2025Updated 7 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆256May 18, 2026Updated last week
- ☆208Nov 17, 2024Updated last year
- Using sparse coding to find distributed representations used by neural networks.☆304Nov 10, 2023Updated 2 years ago
- ☆104Updated this week
- 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.
- Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.☆216Updated this week
- ☆135Oct 28, 2023Updated 2 years ago
- ☆284Oct 1, 2024Updated last year
- ☆60Nov 19, 2024Updated last year
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆876Mar 6, 2026Updated 2 months ago
- Sparse Autoencoder Training Library☆57May 1, 2025Updated last year
- ☆1,096May 20, 2026Updated last week
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆363Jul 23, 2025Updated 10 months ago
- ☆29Apr 4, 2024Updated 2 years ago
- 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.
- open source interpretability platform 🧠☆884Updated this week
- Steering Llama 2 with Contrastive Activation Addition☆231May 23, 2024Updated 2 years ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆27Nov 20, 2024Updated last year
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated last year
- Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)☆65Jul 24, 2025Updated 10 months ago
- Tools for understanding how transformer predictions are built layer-by-layer☆591Aug 7, 2025Updated 9 months ago
- Sparse probing paper full code.☆68Dec 17, 2023Updated 2 years ago
- ☆66Jan 17, 2025Updated last year
- ☆157Feb 16, 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.
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆390Jun 13, 2025Updated 11 months ago
- This repository collects all relevant resources about interpretability in LLMs☆398Nov 1, 2024Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆86Nov 27, 2024Updated last year
- Open source interpretability artefacts for R1.☆175Apr 21, 2025Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆66Oct 27, 2024Updated last year
- Attribution-based Parameter Decomposition☆34Jun 11, 2025Updated 11 months ago
- ☆22Feb 13, 2026Updated 3 months ago