JackCai1206 / arithmetic-self-improveLinks
☆37Updated 8 months ago
Alternatives and similar repositories for arithmetic-self-improve
Users that are interested in arithmetic-self-improve are comparing it to the libraries listed below
Sorting:
- ☆142Updated last month
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆168Updated 4 months ago
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆233Updated 3 months ago
- Open source interpretability artefacts for R1.☆163Updated 6 months ago
- A MAD laboratory to improve AI architecture designs 🧪☆131Updated 10 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated last year
- nanoGPT-like codebase for LLM training☆109Updated 5 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆83Updated 11 months ago
- ☆29Updated last year
- Understand and test language model architectures on synthetic tasks.☆233Updated last month
- Repository for the paper Stream of Search: Learning to Search in Language☆151Updated 8 months ago
- ☆105Updated last week
- Sparse Autoencoder Training Library☆55Updated 5 months ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆193Updated last year
- ☆53Updated last year
- Universal Neurons in GPT2 Language Models☆30Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆219Updated last week
- ☆74Updated last year
- ☆122Updated 8 months ago
- ☆55Updated 11 months ago
- Applying SAEs for fine-grained control☆24Updated 10 months ago
- EvaByte: Efficient Byte-level Language Models at Scale☆110Updated 6 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆224Updated 10 months ago
- ☆86Updated last year
- Attribution-based Parameter Decomposition☆31Updated 4 months ago
- Functional Benchmarks and the Reasoning Gap☆89Updated last year
- Replicating O1 inference-time scaling laws☆90Updated 10 months ago
- ☆83Updated 2 years ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- ☆114Updated 2 weeks ago