KindXiaoming / Omnigrok
Omnigrok: Grokking Beyond Algorithmic Data
☆53Updated 2 years ago
Alternatives and similar repositories for Omnigrok:
Users that are interested in Omnigrok are comparing it to the libraries listed below
- Implementation of OpenAI's 'Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets' paper.☆35Updated last year
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆75Updated 2 years ago
- ☆24Updated 2 years ago
- ☆65Updated 3 months ago
- Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)☆61Updated 3 years ago
- Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.☆165Updated last year
- Universal Neurons in GPT2 Language Models☆27Updated 9 months ago
- ☆13Updated 2 weeks ago
- ☆52Updated 5 months ago
- PyTorch implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆36Updated 3 years ago
- Efficient empirical NTKs in PyTorch☆18Updated 2 years ago
- Deep Learning & Information Bottleneck☆58Updated last year
- ☆60Updated 3 months ago
- ☆24Updated 2 weeks ago
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆35Updated 2 years ago
- ☆61Updated 2 years ago
- ☆30Updated 5 months ago
- ☆26Updated 11 months ago
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆36Updated 2 years ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆44Updated 4 months ago
- ☆26Updated last year
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆58Updated last year
- ☆215Updated 10 months ago
- ☆120Updated last year
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆26Updated 9 months ago
- Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"☆105Updated 4 years ago
- Official repository for our paper, Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Mode…☆15Updated 3 months ago
- ☆16Updated 6 months ago
- Sparse Autoencoder Training Library☆42Updated 4 months ago
- DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule☆59Updated last year