Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"
☆13Jul 18, 2024Updated last year
Alternatives and similar repositories for sae-transfer
Users that are interested in sae-transfer are comparing it to the libraries listed below
Sorting:
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- ☆25Dec 20, 2023Updated 2 years ago
- ☆89Dec 18, 2025Updated 2 months ago
- Reasoning-based Evaluation and Ranking of Translations.☆19Jul 18, 2025Updated 7 months ago
- A library for efficient patching and automatic circuit discovery.☆91Dec 31, 2025Updated 2 months ago
- Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.☆199Updated this week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆248Feb 27, 2026Updated last week
- Sparse Autoencoder Training Library☆55May 1, 2025Updated 10 months ago
- A tiny easily hackable implementation of a feature dashboard.☆15Oct 21, 2025Updated 4 months ago
- ☆153Dec 30, 2025Updated 2 months ago
- ☆134Oct 28, 2023Updated 2 years ago
- ☆22Feb 13, 2026Updated 3 weeks ago
- Algebraic value editing in pretrained language models☆69Nov 1, 2023Updated 2 years ago
- ☆66Feb 16, 2023Updated 3 years ago
- Engine for collecting, uploading, and downloading model activations☆26Apr 2, 2025Updated 11 months ago
- ☆17Feb 14, 2024Updated 2 years ago
- ☆23Jun 30, 2025Updated 8 months ago
- ☆36Apr 30, 2024Updated last year
- ☆27Nov 28, 2024Updated last year
- ☆32Feb 15, 2026Updated 3 weeks ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆84Nov 27, 2024Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆57Oct 30, 2025Updated 4 months ago
- ☆209Oct 14, 2025Updated 4 months ago
- A software for transferring pre-trained English models to foreign languages☆19Mar 20, 2023Updated 2 years ago
- train entropix like a champ!☆20Oct 10, 2024Updated last year
- Applying SAEs for fine-grained control☆25Dec 15, 2024Updated last year
- [NAACL 2022] GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers☆21May 16, 2023Updated 2 years ago
- ☆58Nov 19, 2024Updated last year
- Unified access to Large Language Model modules using NNsight☆101Feb 28, 2026Updated last week
- ☆30Dec 2, 2024Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆64Oct 27, 2024Updated last year
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆29Feb 6, 2026Updated last month
- This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.☆35Oct 28, 2025Updated 4 months ago
- Sparse probing paper full code.☆67Dec 17, 2023Updated 2 years ago
- Auditing agents for fine-tuning safety☆20Oct 21, 2025Updated 4 months ago
- manipulating cointegrated pairs to achieve a market-neutral strategy that outperforms indices☆12Jan 12, 2021Updated 5 years ago
- ☆13Oct 5, 2025Updated 5 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆292Jul 20, 2024Updated last year
- Attribution-based Parameter Decomposition☆34Jun 11, 2025Updated 8 months ago