slavachalnev / SAE-TSLinks
Improving Steering Vectors by Targeting Sparse Autoencoder Features
☆20Updated 7 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.☆67Updated 2 months ago
- ☆101Updated 3 weeks ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆108Updated 4 months ago
- ☆44Updated 7 months ago
- Algebraic value editing in pretrained language models☆65Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆47Updated 8 months ago
- ☆173Updated 2 months ago
- ☆11Updated 11 months ago
- ☆34Updated 5 months ago
- ☆85Updated 10 months ago
- Steering Llama 2 with Contrastive Activation Addition☆158Updated last year
- Sparse Autoencoder Training Library☆52Updated last month
- General-purpose activation steering library☆78Updated last month
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆27Updated last year
- ☆27Updated 4 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆94Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆35Updated 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
- ☆28Updated last year
- ☆95Updated 4 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆185Updated this week
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆22Updated 4 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆95Updated 2 weeks ago
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆58Updated 2 weeks ago
- Attribution-based Parameter Decomposition☆25Updated 2 weeks ago
- ☆131Updated 7 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆75Updated 6 months ago
- ☆31Updated last year
- Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""☆14Updated 8 months ago