callummcdougall / sae_visualizerLinks
☆29Updated last year
Alternatives and similar repositories for sae_visualizer
Users that are interested in sae_visualizer are comparing it to the libraries listed below
Sorting:
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆221Updated 9 months ago
- Sparse Autoencoder Training Library☆54Updated 5 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- ☆127Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆213Updated last week
- ☆34Updated last year
- ☆142Updated 3 weeks ago
- Attribution-based Parameter Decomposition☆30Updated 3 months ago
- ☆242Updated last year
- Mechanistic Interpretability Visualizations using React☆289Updated 9 months ago
- ☆71Updated last month
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- Applying SAEs for fine-grained control☆24Updated 9 months ago
- ☆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
- Steering vectors for transformer language models in Pytorch / Huggingface☆124Updated 7 months ago
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆19Updated last year
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated last week
- A library for efficient patching and automatic circuit discovery.☆77Updated 2 months ago
- ☆54Updated 10 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆80Updated 10 months ago
- Universal Neurons in GPT2 Language Models☆30Updated last year
- Extract full next-token probabilities via language model APIs☆248Updated last year
- Tools for studying developmental interpretability in neural networks.☆103Updated 3 months ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆19Updated 8 months ago
- Erasing concepts from neural representations with provable guarantees☆237Updated 8 months ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆191Updated 2 years ago
- ☆123Updated last year
- A library for mechanistic anomaly detection☆22Updated 8 months ago
- ☆36Updated 7 months ago