Mech-Interp / PySvelte
A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations
☆13Updated 7 months ago
Related projects ⓘ
Alternatives and complementary repositories for PySvelte
- Tools for studying developmental interpretability in neural networks.☆77Updated last week
- ☆106Updated last month
- ☆44Updated last week
- Mechanistic Interpretability Visualizations using React☆200Updated 4 months ago
- Probabilistic programming with HuggingFace language models☆89Updated this week
- Mechanistic Interpretability for Transformer Models☆49Updated 2 years ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆97Updated 2 years ago
- ☆188Updated last month
- Universal Neurons in GPT2 Language Models☆27Updated 5 months ago
- ☆24Updated 7 months ago
- ☆11Updated 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…☆25Updated 6 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆158Updated last month
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆200Updated 9 months ago
- ☆109Updated this week
- ☆76Updated 9 months ago
- ☆54Updated 2 years ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆14Updated 7 months ago
- Sparse Autoencoder Training Library☆28Updated 3 weeks ago
- A library for efficient patching and automatic circuit discovery.☆31Updated last month
- ☆108Updated last year
- ☆146Updated last month
- Sparse and discrete interpretability tool for neural networks☆55Updated 9 months ago
- ☆99Updated 3 months ago
- ☆26Updated last year
- Named Tensors for Legible Deep Learning in JAX☆152Updated this week
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆26Updated 5 months ago
- Composable inference algorithms with LLMs and programmable logic☆17Updated this week
- A domain-specific probabilistic programming language for modeling and inference with language models☆112Updated last year
- Erasing concepts from neural representations with provable guarantees☆210Updated last week