Butanium / tiny-activation-dashboardLinks
A tiny easily hackable implementation of a feature dashboard.
☆13Updated 2 months 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:
- Sparse Autoencoder Training Library☆54Updated 4 months ago
- ☆34Updated last year
- Unified access to Large Language Model modules using NNsight☆44Updated this week
- A library for efficient patching and automatic circuit discovery.☆76Updated last month
- ☆68Updated 2 weeks ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆78Updated 9 months ago
- Attribution-based Parameter Decomposition☆30Updated 3 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆41Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 10 months ago
- Engine for collecting, uploading, and downloading model activations☆22Updated 5 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆211Updated last week
- Applying SAEs for fine-grained control☆23Updated 9 months ago
- A library for training crosscoders☆11Updated 3 months ago
- ☆54Updated 10 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆24Updated 10 months ago
- Tools for optimizing steering vectors in LLMs.☆11Updated 5 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆124Updated 6 months ago
- ☆121Updated this week
- Code repo for the model organisms and convergent directions of EM papers.☆28Updated last month
- 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
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆72Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆19Updated 8 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆201Updated 10 months ago
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆18Updated last year
- ☆142Updated last week
- Universal Neurons in GPT2 Language Models☆30Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆219Updated 9 months ago
- ☆91Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆128Updated 2 months ago