callummcdougall / sae_visualizerLinks
☆28Updated 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).☆211Updated 8 months ago
- Sparse Autoencoder Training Library☆54Updated 3 months ago
- ☆126Updated last year
- ☆32Updated last year
- Attribution-based Parameter Decomposition☆28Updated 2 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆58Updated 9 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆206Updated this week
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 2 years ago
- Mechanistic Interpretability Visualizations using React☆280Updated 8 months ago
- Extract full next-token probabilities via language model APIs☆247Updated last year
- Applying SAEs for fine-grained control☆23Updated 8 months ago
- ☆237Updated 10 months ago
- ☆138Updated 4 months ago
- ☆66Updated last week
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated this week
- ☆111Updated last month
- Erasing concepts from neural representations with provable guarantees☆232Updated 6 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 8 months ago
- ☆105Updated 6 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆122Updated 6 months ago
- 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
- Universal Neurons in GPT2 Language Models☆30Updated last year
- ☆30Updated last year
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆18Updated last year
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆188Updated 2 years ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆191Updated last year
- ☆34Updated 6 months ago
- ☆122Updated last year
- ☆52Updated 9 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆258Updated last year