google-deepmind / mishaxLinks
☆142Updated 3 weeks ago
Alternatives and similar repositories for mishax
Users that are interested in mishax are comparing it to the libraries listed below
Sorting:
- Open source interpretability artefacts for R1.☆159Updated 5 months ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆193Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆221Updated 9 months ago
- Applying SAEs for fine-grained control☆24Updated 9 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
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆80Updated 10 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆203Updated 10 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- code for training & evaluating Contextual Document Embedding models☆197Updated 4 months ago
- Functional Benchmarks and the Reasoning Gap☆89Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆164Updated 3 months ago
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆184Updated 6 months ago
- Training-Ready RL Environments + Evals☆111Updated last week
- Website for hosting the Open Foundation Models Cheat Sheet.☆268Updated 4 months ago
- Scaling is a distributed training library and installable dependency designed to scale up neural networks, with a dedicated module for tr…☆65Updated 11 months ago
- nanoGPT-like codebase for LLM training☆107Updated 4 months ago
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆230Updated 2 months ago
- Extract full next-token probabilities via language model APIs☆248Updated last year
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 8 months ago
- A MAD laboratory to improve AI architecture designs 🧪☆129Updated 9 months ago
- Storing long contexts in tiny caches with self-study☆192Updated 2 weeks ago
- Sparse Autoencoder Training Library☆54Updated 5 months ago
- ☆29Updated last year
- ☆71Updated last month
- Repository for the paper Stream of Search: Learning to Search in Language☆151Updated 8 months ago
- PyTorch library for Active Fine-Tuning☆92Updated this week
- ☆102Updated 5 months ago
- EvaByte: Efficient Byte-level Language Models at Scale☆109Updated 5 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- ☆109Updated 7 months ago