google-deepmind / tracr
☆531Updated 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"☆308Updated 7 months ago
- Language Modeling with the H3 State Space Model☆520Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆489Updated 11 months ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆181Updated last year
- An interactive exploration of Transformer programming.☆262Updated last year
- Neural Networks and the Chomsky Hierarchy☆206Updated last year
- A repository for research on medium sized language models.☆495Updated last week
- Mechanistic Interpretability Visualizations using React☆242Updated 4 months ago
- Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference…☆207Updated 3 months ago
- Used for adaptive human in the loop evaluation of language and embedding models.☆309Updated 2 years ago
- ☆265Updated last year
- Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"☆479Updated 2 years ago
- git extension for {collaborative, communal, continual} model development☆211Updated 5 months ago
- Erasing concepts from neural representations with provable guarantees☆228Updated 3 months ago
- Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch☆407Updated 4 months ago
- Implementation of Memorizing Transformers (ICLR 2022), attention net augmented with indexing and retrieval of memories using approximate …☆632Updated last year
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆201Updated last week
- A puzzle to learn about prompting☆127Updated last year
- Automatic gradient descent☆207Updated last year
- ☆1,007Updated last year
- Convolutions for Sequence Modeling☆878Updated 10 months ago
- Puzzles for exploring transformers☆344Updated 2 years ago
- Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax☆569Updated this week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆199Updated 4 months ago
- Seminar on Large Language Models (COMP790-101 at UNC Chapel Hill, Fall 2022)☆310Updated 2 years ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆211Updated last year
- Scaling Data-Constrained Language Models☆334Updated 7 months ago
- maximal update parametrization (µP)☆1,500Updated 9 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆120Updated 2 years ago
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆345Updated 9 months ago