Sea-Snell / grokking
unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"
☆78Updated 2 years ago
Alternatives and similar repositories for grokking:
Users that are interested in grokking are comparing it to the libraries listed below
- Implementation of OpenAI's 'Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets' paper.☆36Updated last year
- Mechanistic Interpretability for Transformer Models☆50Updated 2 years ago
- Omnigrok: Grokking Beyond Algorithmic Data☆55Updated 2 years ago
- PyTorch implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆36Updated 3 years ago
- ☆62Updated 2 years ago
- Universal Neurons in GPT2 Language Models☆27Updated 10 months ago
- ☆175Updated last year
- Redwood Research's transformer interpretability tools☆14Updated 3 years ago
- A centralized place for deep thinking code and experiments☆82Updated last year
- ☆114Updated 8 months ago
- ☆26Updated last year
- ☆67Updated 4 months ago
- ☆91Updated 2 months ago
- ☆26Updated last year
- Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)☆62Updated 3 years ago
- Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"☆59Updated 3 years ago
- ☆25Updated 2 years ago
- Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implici…☆105Updated last year
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆58Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆120Updated 2 years ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆26Updated 11 months ago
- Tools for studying developmental interpretability in neural networks.☆88Updated 3 months ago
- ☆121Updated last year
- A MAD laboratory to improve AI architecture designs 🧪☆111Updated 4 months ago
- A library for efficient patching and automatic circuit discovery.☆63Updated this week
- ☆51Updated 11 months ago
- Neural Networks and the Chomsky Hierarchy☆205Updated last year
- ☆219Updated 6 months ago
- This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.☆27Updated 7 months ago
- Sparse Autoencoder Training Library☆48Updated 5 months ago