TomFrederik / unseal
Mechanistic Interpretability for Transformer Models
☆50Updated 2 years ago
Alternatives and similar repositories for unseal:
Users that are interested in unseal are comparing it to the libraries listed below
- Utilities for the HuggingFace transformers library☆66Updated 2 years ago
- A library for efficient patching and automatic circuit discovery.☆59Updated last month
- Redwood Research's transformer interpretability tools☆14Updated 2 years ago
- ☆26Updated last year
- ☆26Updated 11 months ago
- ☆121Updated last year
- we got you bro☆35Updated 7 months ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆58Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆116Updated 2 years ago
- ☆19Updated 2 years ago
- ☆61Updated 2 years ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated 2 months ago
- ☆61Updated 4 months ago
- Mechanistic Interpretability Visualizations using React☆233Updated 3 months ago
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆76Updated 2 years ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆197Updated this week
- ☆211Updated 5 months ago
- A dataset of alignment research and code to reproduce it☆74Updated last year
- Sparse Autoencoder Training Library☆43Updated 4 months ago
- ☆113Updated 7 months ago
- ☆35Updated 2 years ago
- A library to create and manage configuration files, especially for machine learning projects.☆77Updated 3 years ago
- ☆89Updated last month
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆30Updated 9 months ago
- Tools for studying developmental interpretability in neural networks.☆86Updated last month
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆181Updated 3 years ago
- ☆22Updated 3 weeks ago
- See the issue board for the current status of active and prospective projects!☆65Updated 3 years ago
- Language-annotated Abstraction and Reasoning Corpus☆83Updated last year
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆177Updated last year