Sparse Autoencoder Training Library
☆55May 1, 2025Updated 10 months ago
Alternatives and similar repositories for e2e_sae
Users that are interested in e2e_sae are comparing it to the libraries listed below
Sorting:
- A TinyStories LM with SAEs and transcoders☆14Apr 3, 2025Updated 10 months ago
- A tiny easily hackable implementation of a feature dashboard.☆15Oct 21, 2025Updated 4 months ago
- ☆150Dec 30, 2025Updated 2 months ago
- ☆22Feb 13, 2026Updated 2 weeks ago
- ☆24Jan 28, 2025Updated last year
- ☆89Dec 18, 2025Updated 2 months ago
- ☆396Aug 21, 2025Updated 6 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆247Updated this week
- Sparsify transformers with SAEs and transcoders☆696Updated this week
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆84Nov 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 …☆243Updated this week
- ☆209Oct 14, 2025Updated 4 months ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated last year
- Sparse Autoencoder for Mechanistic Interpretability☆292Jul 20, 2024Updated last year
- ☆25Dec 20, 2023Updated 2 years ago
- ☆17Feb 14, 2024Updated 2 years ago
- ☆33Jul 9, 2025Updated 7 months ago
- A library for efficient patching and automatic circuit discovery.☆90Dec 31, 2025Updated 2 months ago
- ☆19Mar 5, 2024Updated last year
- ☆134Oct 28, 2023Updated 2 years ago
- A library for training crosscoders☆16May 28, 2025Updated 9 months ago
- Codebase for "On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback". This repo implements a generative multi-tur…☆23Dec 3, 2024Updated last year
- Trains Sparse Autoencoders based on outputs from language models☆11Oct 7, 2024Updated last year
- Training Sparse Autoencoders on Language Models☆1,219Updated this week
- Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.☆194Feb 18, 2026Updated last week
- ☆30Aug 2, 2024Updated last year
- ☆36Apr 30, 2024Updated last year
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆27Nov 20, 2024Updated last year
- Mamba support for transformer lens☆19Sep 17, 2024Updated last year
- Repository with sample code using Apollo's suggested engineering practices☆15Dec 16, 2024Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆825Updated this week
- Algebraic value editing in pretrained language models☆68Nov 1, 2023Updated 2 years ago
- ☆71Jul 24, 2025Updated 7 months ago
- HypotheSAEs: hypothesizing interpretable relationships in text datasets using sparse autoencoders. https://arxiv.org/abs/2502.04382☆77Updated this week
- ☆17Updated this week
- Official codebase for "Analyzing the Generalization and Reliability of Steering Vectors"☆19Dec 14, 2024Updated last year
- Unified access to Large Language Model modules using NNsight☆93Updated this week
- Attribution-based Parameter Decomposition☆34Jun 11, 2025Updated 8 months ago
- ☆199Nov 17, 2024Updated last year