☆134Oct 28, 2023Updated 2 years ago
Alternatives and similar repositories for 1L-Sparse-Autoencoder
Users that are interested in 1L-Sparse-Autoencoder are comparing it to the libraries listed below
Sorting:
- Using sparse coding to find distributed representations used by neural networks.☆297Nov 10, 2023Updated 2 years ago
- Sparse Autoencoder for Mechanistic Interpretability☆292Jul 20, 2024Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆247Updated this week
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated last year
- ☆396Aug 21, 2025Updated 6 months ago
- Training Sparse Autoencoders on Language Models☆1,219Updated this week
- Sparse Autoencoder Training Library☆55May 1, 2025Updated 10 months ago
- An Open Source Implementation of Anthropic's Paper: "Towards Monosemanticity: Decomposing Language Models with Dictionary Learning"☆57May 12, 2024Updated last year
- ☆58Nov 19, 2024Updated last year
- ☆209Oct 14, 2025Updated 4 months ago
- A library for mechanistic interpretability of GPT-style language models☆3,112Updated this week
- ☆25Dec 20, 2023Updated 2 years ago
- Mechanistic Interpretability Visualizations using React☆326Dec 18, 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
- Sparsify transformers with SAEs and transcoders☆696Updated this week
- ☆571Jul 19, 2024Updated last year
- A very hacky set of functions for getting plotly to do what I want when doing mech interp research, designed to be compatible with PyTorc…☆11Jun 16, 2023Updated 2 years ago
- ☆271Oct 1, 2024Updated last year
- ☆100Aug 8, 2024Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆825Updated this week
- ☆22Feb 13, 2026Updated 2 weeks ago
- ☆17Feb 14, 2024Updated 2 years ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆84Nov 27, 2024Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆137Sep 14, 2022Updated 3 years ago
- ☆199Nov 17, 2024Updated last year
- ☆12Jul 12, 2024Updated last year
- ☆155Feb 16, 2026Updated 2 weeks ago
- ☆25Sep 5, 2024Updated last year
- Modified to support crosscoder training.☆25Feb 4, 2026Updated 3 weeks ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆47May 31, 2024Updated last year
- ☆12Oct 23, 2022Updated 3 years ago
- Experiments with representation engineering☆13Feb 28, 2024Updated 2 years ago
- ☆30Aug 2, 2024Updated last year
- ☆1,072Mar 6, 2024Updated last year
- Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)☆60Jul 24, 2025Updated 7 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆64Oct 27, 2024Updated last year
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆863Jan 29, 2026Updated last month
- This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.☆34Oct 28, 2025Updated 4 months ago
- ☆66Feb 16, 2023Updated 3 years ago