scienceetonnante / grokkingLinks
Demonstration of the grokking phenomenon in machine learning in a simple case
☆61Updated 7 months ago
Alternatives and similar repositories for grokking
Users that are interested in grokking are comparing it to the libraries listed below
Sorting:
- Probabilistic programming with large language models☆136Updated 2 months ago
- The boundary of neural network trainability is fractal☆216Updated last year
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆309Updated 2 months ago
- Tools for studying developmental interpretability in neural networks.☆103Updated 3 months ago
- ☆345Updated last month
- My writings about ARC (Abstraction and Reasoning Corpus)☆84Updated 3 weeks ago
- Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.☆173Updated 2 years ago
- 🔬 Interpretability for Leela Chess Zero networks.☆16Updated 3 weeks ago
- Automated Research Assistant☆63Updated this week
- A framework for conducting machine learning experiments in python☆41Updated 9 months ago
- Reverse Engineering the Abstraction and Reasoning Corpus☆305Updated 7 months ago
- Mechanistic Interpretability Visualizations using React☆289Updated 9 months ago
- 🧠 Starter templates for doing interpretability research☆74Updated 2 years ago
- Sparse Autoencoder for Mechanistic Interpretability☆267Updated last year
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆227Updated last month
- ☆83Updated last year
- LENS Project☆50Updated last year
- ☆30Updated last year
- Uncertainty quantification with PyTorch☆372Updated this week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆220Updated 9 months ago
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆810Updated 3 weeks ago
- Making your benchmark of optimization algorithms simple and open☆268Updated last week
- A lightweight library for Bayesian analysis of LLM evals (ICML 2025 Spotlight Position Paper)☆21Updated 3 months ago
- Parameter-Free Optimizers for Pytorch☆130Updated last year
- ☆127Updated last year
- ☆546Updated last year
- ☆65Updated 10 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- Hierarchical Associative Memory User Experience☆103Updated 2 months ago
- ☆242Updated 11 months ago