jacobdunefsky / llm-steering-optLinks
Tools for optimizing steering vectors in LLMs.
☆18Updated 9 months ago
Alternatives and similar repositories for llm-steering-opt
Users that are interested in llm-steering-opt are comparing it to the libraries listed below
Sorting:
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆45Updated last year
- Sparse Autoencoder Training Library☆56Updated 8 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆63Updated last year
- ☆20Updated 9 months ago
- Trains Sparse Autoencoders based on outputs from language models☆11Updated last year
- ☆57Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆162Updated 7 months ago
- A library for efficient patching and automatic circuit discovery.☆86Updated 3 weeks ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆26Updated last year
- Modified to support crosscoder training.☆25Updated 2 weeks ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆235Updated last week
- 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 last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆138Updated 11 months ago
- ☆58Updated last year
- ☆204Updated 3 months ago
- ☆142Updated last month
- Steering Llama 2 with Contrastive Activation Addition☆206Updated last year
- A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.☆54Updated this week
- A benchmark for mechanistic discovery of circuits in Transformers☆16Updated last year
- Code repo for the model organisms and convergent directions of EM papers.☆45Updated 4 months ago
- ☆114Updated 11 months ago
- ☆195Updated last year
- ☆70Updated 6 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆57Updated 3 months ago
- ☆51Updated 2 years ago
- Unified access to Large Language Model modules using NNsight☆81Updated 2 weeks ago
- [ICLR 2025] General-purpose activation steering library☆137Updated 4 months ago
- A tiny easily hackable implementation of a feature dashboard.☆15Updated 3 months ago
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆28Updated 11 months ago
- ☆99Updated last year