Alternatives and similar repositories for grokking

Users that are interested in grokking are comparing it to the libraries listed below

• likenneth / othello_world
  Emergent world representations: Exploring a sequence model trained on a synthetic task
  ☆191Updated 2 years ago
• danielmamay / grokking
  Implementation of OpenAI's 'Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets' paper.
  ☆39Updated 2 years ago
• GFNOrg / gfn-lm-tuning
  ☆185Updated last year
• anthropics / toy-models-of-superposition
  Notebooks accompanying Anthropic's "Toy Models of Superposition" paper
  ☆130Updated 3 years ago
• ethancaballero / broken_neural_scaling_laws
  Code Release for "Broken Neural Scaling Laws" (BNSL) paper
  ☆59Updated 2 years ago
• andyljones / boardlaw
  Scaling scaling laws with board games.
  ☆53Updated 2 years ago
• KindXiaoming / Omnigrok
  Omnigrok: Grokking Beyond Algorithmic Data
  ☆62Updated 2 years ago
• TomFrederik / unseal
  Mechanistic Interpretability for Transformer Models
  ☆53Updated 3 years ago
• bilal-chughtai / rep-theory-mech-interp
  ☆27Updated 2 years ago
• epfml / llm-baselines
  nanoGPT-like codebase for LLM training
  ☆109Updated last week
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆133Updated 10 months ago
• edwardjhu / TP4
  Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)
  ☆63Updated 4 years ago
• taufeeque9 / codebook-features
  Sparse and discrete interpretability tool for neural networks
  ☆64Updated last year
• google-deepmind / neural_networks_chomsky_hierarchy
  Neural Networks and the Chomsky Hierarchy
  ☆211Updated last year
• srush / do-we-need-attention
  ☆166Updated 2 years ago
• princeton-nlp / TransformerPrograms
  [NeurIPS 2023] Learning Transformer Programs
  ☆162Updated last year
• davisyoshida / lorax
  LoRA for arbitrary JAX models and functions
  ☆142Updated last year
• Sea-Snell / JAXSeq
  Train very large language models in Jax.
  ☆210Updated 2 years ago
• callummcdougall / sae_visualizer
  ☆29Updated last year
• understanding-search / maze-transformer
  This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.
  ☆32Updated 2 weeks ago
• mechanistic-interpretability-grokking / progress-measures-paper
  ☆70Updated 3 years ago
• aks2203 / deep-thinking
  A centralized place for deep thinking code and experiments
  ☆87Updated 2 years ago
• victorvikram / ConceptARC
  Materials for ConceptARC paper
  ☆105Updated last year
• redwoodresearch / Easy-Transformer
  ☆129Updated last year
• clement-bonnet / lpn
  Latent Program Network (from the "Searching Latent Program Spaces" paper)
  ☆103Updated last month
• lee-ny / teaching_arithmetic
  ☆83Updated 2 years ago
• KihoPark / linear_rep_geometry
  ☆109Updated 9 months ago
• nostalgebraist / transformer-utils
  Utilities for the HuggingFace transformers library
  ☆72Updated 2 years ago
• Ping-C / optimizer
  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
• p-lambda / incontext-learning
  Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implici…
  ☆106Updated 2 years ago