Butanium / tiny-activation-dashboardLinks
A tiny easily hackable implementation of a feature dashboard.
☆12Updated last month
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☆44Updated this week
- ☆53Updated 9 months ago
- ☆33Updated last year
- 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
- Sparse Autoencoder Training Library☆54Updated 3 months ago
- A library for efficient patching and automatic circuit discovery.☆76Updated last month
- Engine for collecting, uploading, and downloading model activations☆22Updated 4 months ago
- ☆68Updated this week
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆19Updated 7 months ago
- Attribution-based Parameter Decomposition☆29Updated 2 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆40Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆58Updated 10 months ago
- Modified to support crosscoder training.☆22Updated last month
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆214Updated 8 months ago
- ☆116Updated last month
- ☆126Updated last year
- ☆15Updated 4 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆122Updated 6 months ago
- Applying SAEs for fine-grained control☆23Updated 8 months ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆12Updated last year
- ☆238Updated 10 months ago
- Mechanistic Interpretability Visualizations using React☆281Updated 8 months ago
- MishformerLens intends to be a drop-in replacement for TransformerLens that AST patches HuggingFace Transformers rather than implementing…☆10Updated 10 months ago
- ☆184Updated last month
- Steering Llama 2 with Contrastive Activation Addition☆176Updated last year
- ☆90Updated last year
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆19Updated 10 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 9 months ago
- Algebraic value editing in pretrained language models☆65Updated last year
- ☆29Updated last year