google-deepmind / tracr
☆525Updated last year
Alternatives and similar repositories for tracr:
Users that are interested in tracr are comparing it to the libraries listed below
- An interpreter for RASP as described in the ICML 2021 paper "Thinking Like Transformers"☆304Updated 6 months ago
- Tools for understanding how transformer predictions are built layer-by-layer☆480Updated 9 months ago
- An interactive exploration of Transformer programming.☆261Updated last year
- Neural Networks and the Chomsky Hierarchy☆204Updated 11 months ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆177Updated last year
- Mechanistic Interpretability Visualizations using React☆233Updated 3 months ago
- Language Modeling with the H3 State Space Model☆516Updated last year
- Convolutions for Sequence Modeling☆878Updated 9 months ago
- Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate …☆631Updated last year
- ☆263Updated last year
- Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference…☆204Updated 2 months ago
- Erasing concepts from neural representations with provable guarantees☆226Updated last month
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆186Updated 9 months ago
- git extension for {collaborative, communal, continual} model development☆208Updated 4 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆197Updated this week
- Extract full next-token probabilities via language model APIs☆233Updated last year
- Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"☆476Updated 2 years ago
- A puzzle to learn about prompting☆124Updated last year
- ☆253Updated 2 years ago
- ViT Prisma is a mechanistic interpretability library for Vision Transformers (ViTs).☆214Updated last week
- Used for adaptive human in the loop evaluation of language and embedding models.☆306Updated 2 years ago
- Puzzles for exploring transformers☆333Updated last year
- ☆343Updated 11 months ago
- Automatic gradient descent☆207Updated last year
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax☆557Updated this week
- ☆211Updated 5 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆189Updated 3 months ago
- Tools for studying developmental interpretability in neural networks.☆86Updated last month
- Ask Me Anything language model prompting☆546Updated last year
- Code for Parsel 🐍 - generate complex programs with language models☆424Updated last year