Mech-Interp / PySvelte
A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations
☆14Updated 11 months ago
Alternatives and similar repositories for PySvelte:
Users that are interested in PySvelte are comparing it to the libraries listed below
- ☆61Updated 4 months ago
- Mechanistic Interpretability for Transformer Models☆50Updated 2 years ago
- Redwood Research's transformer interpretability tools☆14Updated 2 years ago
- Universal Neurons in GPT2 Language Models☆27Updated 9 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆26Updated 10 months ago
- ☆12Updated this week
- Steering vectors for transformer language models in Pytorch / Huggingface☆90Updated last month
- A library for efficient patching and automatic circuit discovery.☆59Updated last month
- ☆26Updated 11 months ago
- ☆61Updated 2 years ago
- Code associated to papers on superposition (in ML interpretability)☆28Updated 2 years ago
- ☆211Updated 5 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆117Updated 2 years ago
- Tools for studying developmental interpretability in neural networks.☆86Updated 2 months ago
- ☆26Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆46Updated 4 months ago
- ☆25Updated last month
- ☆34Updated 3 weeks ago
- ☆29Updated 10 months ago
- Sparse Autoencoder Training Library☆43Updated 4 months ago
- ☆89Updated last month
- Erasing concepts from neural representations with provable guarantees☆226Updated last month
- Experiments with representation engineering☆11Updated last year
- ☆51Updated 10 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆163Updated this week
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated 2 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆189Updated 3 months ago
- ☆32Updated 4 months ago
- Probabilistic programming with HuggingFace language models☆104Updated this week
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆30Updated 9 months ago