UlisseMini / activation_additions_hfLinks
Reimplementation of https://github.com/montemac/algebraic_value_editing in pure PyTorch for efficiency on large models
☆13Updated 2 years ago
Alternatives and similar repositories for activation_additions_hf
Users that are interested in activation_additions_hf are comparing it to the libraries listed below
Sorting:
- Tools for studying developmental interpretability in neural networks.☆103Updated 3 months ago
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆14Updated last year
- Attribution-based Parameter Decomposition☆30Updated 3 months ago
- ☆242Updated 11 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- Mechanistic Interpretability Visualizations using React☆289Updated 9 months ago
- 🧠 Starter templates for doing interpretability research☆74Updated 2 years ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated this week
- Decoder only transformer, built from scratch with PyTorch☆31Updated last year
- ☆127Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆220Updated 9 months ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆19Updated 8 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆124Updated 7 months ago
- ☆34Updated last year
- Sparse Autoencoder Training Library☆54Updated 4 months ago