slavachalnev / SAE-TSLinks
Improving Steering Vectors by Targeting Sparse Autoencoder Features
☆20Updated 6 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☆55Updated 7 months ago
- A library for efficient patching and automatic circuit discovery.☆65Updated last month
- ☆43Updated 6 months ago
- Algebraic value editing in pretrained language models☆65Updated last year
- ☆97Updated last month
- ☆83Updated 9 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆101Updated 3 months ago
- ☆33Updated 4 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆34Updated last year
- Sparse Autoencoder Training Library☆50Updated last month
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆26Updated last year
- Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""☆14Updated 7 months ago
- Applying SAEs for fine-grained control☆18Updated 5 months ago
- Code to enable layer-level steering in LLMs using sparse auto encoders☆17Updated 3 weeks ago
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆56Updated 3 months ago
- General-purpose activation steering library☆74Updated 3 weeks ago
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆23Updated 3 months ago
- ☆62Updated last week
- ☆34Updated 2 weeks ago
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆16Updated 7 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆89Updated last week
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆47Updated 7 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆93Updated last year
- A small package implementing some useful wrapping around nnsight☆13Updated last month
- ☆14Updated 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…☆11Updated 4 months ago
- ☆120Updated 6 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated 2 months ago
- ☆28Updated last year
- ☆44Updated last year