Sea-Snell / grokkingLinks
unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"
☆79Updated 3 years ago
Alternatives and similar repositories for grokking
Users that are interested in grokking are comparing it to the libraries listed below
Sorting:
- Implementation of OpenAI's 'Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets' paper.☆39Updated 2 years ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆191Updated 2 years ago
- Omnigrok: Grokking Beyond Algorithmic Data☆62Updated 2 years ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- Neural Networks and the Chomsky Hierarchy☆210Updated last year
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆59Updated last year
- ☆185Updated last year
- ☆83Updated 2 years ago
- ☆69Updated 3 years ago
- nanoGPT-like codebase for LLM training☆109Updated 5 months ago
- Mechanistic Interpretability for Transformer Models☆53Updated 3 years ago
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆40Updated 2 years ago
- ☆126Updated last year
- Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)☆63Updated 4 years ago
- ☆27Updated 2 years ago
- ☆166Updated 2 years ago
- [NeurIPS 2023] Learning Transformer Programs☆162Updated last year
- Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implici…☆108Updated last year
- A MAD laboratory to improve AI architecture designs 🧪☆131Updated 10 months ago
- Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"☆59Updated 3 years ago
- ☆240Updated last year
- Sparse Autoencoder Training Library☆55Updated 5 months ago
- ☆107Updated 8 months ago
- Tools for studying developmental interpretability in neural networks.☆111Updated 4 months ago
- Universal Neurons in GPT2 Language Models☆30Updated last year
- Train very large language models in Jax.☆209Updated 2 years ago
- LoRA for arbitrary JAX models and functions☆141Updated last year
- ☆26Updated 2 years ago
- A library to create and manage configuration files, especially for machine learning projects.☆80Updated 3 years ago
- PyTorch implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆37Updated 3 years ago