likenneth / othello_worldLinks
Emergent world representations: Exploring a sequence model trained on a synthetic task
☆191Updated 2 years ago
Alternatives and similar repositories for othello_world
Users that are interested in othello_world are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2023] Learning Transformer Programs☆162Updated last year
- ☆123Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- ☆276Updated last year
- ☆127Updated last year
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated last week
- ☆210Updated 2 years ago
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆79Updated 3 years ago
- ☆242Updated last year
- ☆186Updated last year
- ☆69Updated 2 years ago
- Mechanistic Interpretability for Transformer Models☆52Updated 3 years ago
- A library for efficient patching and automatic circuit discovery.☆77Updated 2 months ago
- Tools for understanding how transformer predictions are built layer-by-layer☆527Updated last month
- Erasing concepts from neural representations with provable guarantees☆237Updated 8 months ago
- Materials for ConceptARC paper☆103Updated 10 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆221Updated 9 months ago
- ☆106Updated 7 months ago
- Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference…☆211Updated 4 months ago
- Sparse Autoencoder Training Library☆54Updated 5 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆213Updated last week
- ☆83Updated 2 years ago
- Utilities for the HuggingFace transformers library☆72Updated 2 years ago
- ☆138Updated 2 months ago
- A repository for transformer critique learning and generation☆90Updated last year
- Mechanistic Interpretability Visualizations using React☆289Updated 9 months ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆193Updated last year
- Official code from the paper "Offline RL for Natural Language Generation with Implicit Language Q Learning"☆209Updated 2 years ago
- Neural Networks and the Chomsky Hierarchy☆209Updated last year
- Understand and test language model architectures on synthetic tasks.☆229Updated last week