slavachalnev / SAE-TSLinks
Improving Steering Vectors by Targeting Sparse Autoencoder Features
☆24Updated 10 months ago
Alternatives and similar repositories for SAE-TS
Users that are interested in SAE-TS are comparing it to the libraries listed below
Sorting:
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- ☆54Updated 10 months ago
- ☆125Updated 2 weeks ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆134Updated 3 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆125Updated 7 months ago
- A library for efficient patching and automatic circuit discovery.☆77Updated 2 months ago
- ☆187Updated 2 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆215Updated this week
- Sparse Autoencoder Training Library☆54Updated 5 months ago
- Algebraic value editing in pretrained language models☆66Updated last year
- ☆174Updated 10 months ago
- ☆48Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆97Updated 2 years ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆182Updated last year
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆117Updated last year
- ☆91Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆54Updated last year
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆61Updated 3 months ago
- 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…☆12Updated 8 months ago
- Code to enable layer-level steering in LLMs using sparse auto encoders☆26Updated 2 weeks ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆41Updated last year
- [ICLR 2025] General-purpose activation steering library☆107Updated 2 weeks ago
- ☆78Updated 4 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆80Updated 6 months ago
- ☆106Updated 7 months ago
- ☆123Updated last year
- ☆15Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆80Updated 10 months ago
- ☆23Updated 8 months ago