Butanium / tiny-activation-dashboardLinks
A tiny easily hackable implementation of a feature dashboard.
☆12Updated 2 weeks ago
Alternatives and similar repositories for tiny-activation-dashboard
Users that are interested in tiny-activation-dashboard are comparing it to the libraries listed below
Sorting:
- Unified access to Large Language Model modules using NNsight☆21Updated this week
- Engine for collecting, uploading, and downloading model activations☆20Updated 3 months ago
- A library for efficient patching and automatic circuit discovery.☆70Updated 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 …☆193Updated this week
- ☆47Updated 8 months ago
- ☆32Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆40Updated last year
- Sparse Autoencoder Training Library☆53Updated 2 months ago
- Mechanistic Interpretability Visualizations using React☆262Updated 7 months ago
- ☆105Updated last month
- Steering vectors for transformer language models in Pytorch / Huggingface☆115Updated 4 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆57Updated 8 months ago
- ☆123Updated last year
- ☆231Updated 9 months ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated 6 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆206Updated 7 months ago
- ☆182Updated 3 months ago
- ☆15Updated 3 months ago
- ☆60Updated last week
- Experiments with representation engineering☆12Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆164Updated last year
- Modified to support crosscoder training.☆20Updated 2 weeks ago
- Algebraic value editing in pretrained language models☆65Updated last year
- Applying SAEs for fine-grained control☆22Updated 7 months ago
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆19Updated 9 months ago
- Attribution-based Parameter Decomposition☆27Updated last month
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 7 months ago
- ☆146Updated 8 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆95Updated last year
- A toolkit for describing model features and intervening on those features to steer behavior.☆193Updated 8 months ago