TomFrederik / unsealLinks
Mechanistic Interpretability for Transformer Models
☆53Updated 3 years ago
Alternatives and similar repositories for unseal
Users that are interested in unseal are comparing it to the libraries listed below
Sorting:
- Utilities for the HuggingFace transformers library☆73Updated 2 years ago
- Redwood Research's transformer interpretability tools☆14Updated 3 years ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆216Updated 2 weeks ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆197Updated 2 years ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆132Updated 3 years ago
- Erasing concepts from neural representations with provable guarantees☆242Updated 11 months ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Updated 11 months ago
- ☆132Updated 2 years ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆59Updated 2 years ago
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆201Updated 4 years ago
- ☆28Updated 2 years ago
- Sparse Autoencoder Training Library☆56Updated 8 months ago
- Tools for studying developmental interpretability in neural networks.☆119Updated last week
- ☆283Updated last year
- Mechanistic Interpretability Visualizations using React☆306Updated last year
- A dataset of alignment research and code to reproduce it☆78Updated 2 years ago
- Language-annotated Abstraction and Reasoning Corpus☆98Updated 2 years ago
- ☆56Updated 2 years ago
- ☆262Updated last year
- ☆135Updated last year
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆20Updated 2 months ago
- A library for efficient patching and automatic circuit discovery.☆84Updated last week
- A library to create and manage configuration files, especially for machine learning projects.☆79Updated 3 years ago
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers☆42Updated 10 months ago
- See the issue board for the current status of active and prospective projects!☆65Updated 3 years ago
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆81Updated 3 years ago
- we got you bro☆36Updated last year
- ☆29Updated last year
- The Happy Faces Benchmark☆15Updated 2 years ago
- Experiments with representation engineering☆13Updated last year