slavachalnev / SAE-TSView external linksLinks
Improving Steering Vectors by Targeting Sparse Autoencoder Features
☆27Nov 20, 2024Updated last year
Alternatives and similar repositories for SAE-TS
Users that are interested in SAE-TS are comparing it to the libraries listed below
Sorting:
- Applying SAEs for fine-grained control☆25Dec 15, 2024Updated last year
- James' cookbook of evaluations and finetuning experiments☆21Feb 3, 2026Updated 2 weeks ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆64Oct 27, 2024Updated last year
- Redwood Research's transformer interpretability tools☆15Apr 15, 2022Updated 3 years ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆209May 23, 2024Updated last year
- ☆394Aug 21, 2025Updated 5 months ago
- Code to enable layer-level steering in LLMs using sparse auto encoders☆29Sep 18, 2025Updated 4 months ago
- Algebraic value editing in pretrained language models☆68Nov 1, 2023Updated 2 years ago
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆20Oct 18, 2024Updated last year
- The AI that helps you achieve your goals☆11Feb 4, 2024Updated 2 years ago
- ☆58Jan 17, 2025Updated last year
- ☆28Nov 16, 2025Updated 3 months ago
- ☆12Jul 12, 2024Updated last year
- A tiny easily hackable implementation of a feature dashboard.☆15Oct 21, 2025Updated 3 months ago
- Experiments with representation engineering☆13Feb 28, 2024Updated last year
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆13Jan 26, 2025Updated last year
- ☆12Oct 23, 2022Updated 3 years ago
- ☆19Aug 4, 2025Updated 6 months ago
- ☆10May 17, 2024Updated last year
- Code repository for "RL Grokking Recipe: How RL Unlocks and Transfers New Algorithms in LLMs""☆29Oct 12, 2025Updated 4 months ago
- [ICLR 2025] "Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond"☆17Feb 27, 2025Updated 11 months ago
- [ICLR 2025] General-purpose activation steering library☆142Sep 18, 2025Updated 4 months ago
- Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.☆177Feb 9, 2026Updated last week
- ☆17Feb 14, 2024Updated 2 years ago
- ☆16Mar 5, 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 …☆241Feb 9, 2026Updated last week
- ☆17Updated this week
- Implementation of Influence Function approximations for differently sized ML models, using PyTorch☆16Sep 15, 2023Updated 2 years ago
- [ICLR 2022] Official Code Repository for "TRGP: TRUST REGION GRADIENT PROJECTION FOR CONTINUAL LEARNING"☆22Oct 5, 2022Updated 3 years ago
- (Model-written) LLM evals library☆18Dec 13, 2024Updated last year
- Training Sparse Autoencoders on Language Models☆1,201Updated this week
- Machine Learning for Alignment Bootcamp☆81Apr 27, 2022Updated 3 years ago
- ☆25Nov 11, 2025Updated 3 months ago
- Efficient Dictionary Learning with Switch Sparse Autoencoders (SAEs)☆25Dec 1, 2024Updated last year
- Code for "Evidence of Learned Look-Ahead in a Chess-Playing Neural Network"☆26Jun 4, 2024Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆140Feb 21, 2025Updated 11 months ago
- ☆25Apr 23, 2024Updated last year
- ☆58Nov 19, 2024Updated last year