Kiv / fancy_einsumLinks
Einsum with einops style variable names
☆17Updated last year
Alternatives and similar repositories for fancy_einsum
Users that are interested in fancy_einsum are comparing it to the libraries listed below
Sorting:
- Tools for studying developmental interpretability in neural networks.☆101Updated 2 months ago
- The Happy Faces Benchmark☆15Updated 2 years ago
- ☆18Updated 2 years ago
- (Model-written) LLM evals library☆18Updated 8 months ago
- Mechanistic Interpretability Visualizations using React☆281Updated 8 months ago
- ☆63Updated 2 years ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 2 years ago
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆195Updated 3 years ago
- 🧱 Modula software package☆225Updated last week
- METR Task Standard☆159Updated 6 months ago
- ☆126Updated last year
- See the issue board for the current status of active and prospective projects!☆65Updated 3 years ago
- Extract full next-token probabilities via language model APIs☆247Updated last year
- Neural Networks and the Chomsky Hierarchy☆208Updated last year
- Mechanistic Interpretability for Transformer Models☆51Updated 3 years ago
- Erasing concepts from neural representations with provable guarantees☆232Updated 7 months ago
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆14Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆214Updated 8 months ago
- ☆238Updated 10 months ago
- Machine Learning for Alignment Bootcamp☆78Updated 3 years ago
- An interactive exploration of Transformer programming.☆269Updated last year
- ☆84Updated last year
- ☆19Updated last year
- ☆68Updated 2 years ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆223Updated 2 weeks ago
- Probabilistic programming with large language models☆133Updated last month
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated this week
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆88Updated this week
- ☆276Updated last year
- Redwood Research's transformer interpretability tools☆14Updated 3 years ago