scienceetonnante / grokkingLinks
Demonstration of the grokking phenomenon in machine learning in a simple case
☆58Updated 6 months ago
Alternatives and similar repositories for grokking
Users that are interested in grokking are comparing it to the libraries listed below
Sorting:
- Tools for studying developmental interpretability in neural networks.☆100Updated last month
- The boundary of neural network trainability is fractal☆215Updated last year
- Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.☆172Updated 2 years ago
- Benchmarks for the Evaluation of LLM Supervision☆32Updated last month
- Uncertainty quantification with PyTorch☆367Updated 3 months ago
- 🧠 Starter templates for doing interpretability research☆73Updated 2 years ago
- Neural Networks and the Chomsky Hierarchy☆207Updated last year
- LENS Project☆48Updated last year
- Subject of the hackathon 42☆11Updated 2 years ago
- Parameter-Free Optimizers for Pytorch☆130Updated last year
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆292Updated 2 weeks ago
- An interactive exploration of Transformer programming.☆267Updated last year
- ☆540Updated last year
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆78Updated 3 years ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆186Updated 2 years ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆220Updated last year
- epsilon machines and transformers!☆28Updated last month
- A package for statistically rigorous scientific discovery using machine learning. Implements prediction-powered inference.☆253Updated 2 months ago
- Making your benchmark of optimization algorithms simple and open☆266Updated last week
- My writings about ARC (Abstraction and Reasoning Corpus)☆79Updated last week
- ☆326Updated 3 weeks ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆207Updated 7 months ago
- Compositional Linear Algebra☆487Updated last week
- Machine Learning for Alignment Bootcamp☆25Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆128Updated 2 years ago
- Probabilistic programming with large language models☆129Updated 2 weeks ago
- ☆20Updated 3 months ago
- Erasing concepts from neural representations with provable guarantees☆232Updated 6 months ago
- Code for 1st place solution to Kaggle's Abstraction and Reasoning Challenge☆159Updated last month
- Tools for understanding how transformer predictions are built layer-by-layer☆512Updated last year