amack315 / unsupervised-steering-vectorsLinks
☆32Updated last year
Alternatives and similar repositories for unsupervised-steering-vectors
Users that are interested in unsupervised-steering-vectors are comparing it to the libraries listed below
Sorting:
- Sparse Autoencoder Training Library☆54Updated 3 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆58Updated 10 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆207Updated this week
- ☆67Updated 2 weeks ago
- ☆53Updated 9 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆212Updated 8 months ago
- Applying SAEs for fine-grained control☆23Updated 8 months ago
- Attribution-based Parameter Decomposition☆28Updated 2 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆122Updated 6 months ago
- ☆238Updated 10 months ago
- ☆126Updated last year
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆24Updated 9 months ago
- ☆114Updated last month
- A library for efficient patching and automatic circuit discovery.☆76Updated last month
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 9 months ago
- ☆184Updated last month
- A tiny easily hackable implementation of a feature dashboard.☆12Updated last month
- Inference API for many LLMs and other useful tools for empirical research☆66Updated last week
- ☆30Updated last year
- 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
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆12Updated last year
- Universal Neurons in GPT2 Language Models☆30Updated last year
- ☆29Updated last year
- Unified access to Large Language Model modules using NNsight☆42Updated this week
- A toolkit for describing model features and intervening on those features to steer behavior.☆198Updated 9 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 2 years ago
- ☆139Updated last week
- Mechanistic Interpretability Visualizations using React☆281Updated 8 months ago
- Steering Llama 2 with Contrastive Activation Addition☆176Updated last year
- ☆163Updated 9 months ago