Mech-Interp / PySvelte
A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations
☆13Updated 6 months ago
Related projects ⓘ
Alternatives and complementary repositories for PySvelte
- ☆43Updated 4 months ago
- Tools for studying developmental interpretability in neural networks.☆74Updated this week
- Mechanistic Interpretability Visualizations using React☆195Updated 3 months ago
- ☆186Updated last month
- ☆102Updated last month
- ☆24Updated 7 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆157Updated last month
- Named Tensors for Legible Deep Learning in JAX☆153Updated this week
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆95Updated 2 years ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆194Updated 9 months ago
- ☆108Updated last year
- ☆96Updated 3 months ago
- Scalable neural net training via automatic normalization in the modular norm.☆118Updated 2 months ago
- Universal Neurons in GPT2 Language Models☆26Updated 5 months ago
- Sparse Autoencoder Training Library☆26Updated last week
- Mechanistic Interpretability for Transformer Models☆49Updated 2 years ago
- Probabilistic programming with HuggingFace language models☆88Updated 2 weeks ago
- ☆141Updated 2 weeks ago
- ☆99Updated this week
- ☆48Updated 8 months ago
- A library for efficient patching and automatic circuit discovery.☆30Updated last month
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆25Updated 5 months ago
- A simple library for scaling up JAX programs☆125Updated last week
- ☆58Updated 2 years ago
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆172Updated 2 years ago
- Sparse Autoencoder for Mechanistic Interpretability☆187Updated 3 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆26Updated 5 months ago
- Erasing concepts from neural representations with provable guarantees☆208Updated 3 weeks ago
- Minimal but scalable implementation of large language models in JAX☆25Updated last week
- 🧠 Starter templates for doing interpretability research☆63Updated last year