unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"
☆90Jul 4, 2022Updated 3 years ago
Alternatives and similar repositories for grokking
Users that are interested in grokking are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Omnigrok: Grokking Beyond Algorithmic Data☆64Feb 24, 2023Updated 3 years ago
- ☆12Jul 30, 2025Updated 9 months ago
- A machine learning library capable of training various deep neural networks (RNNs, LSTMs, DBNs, ect...) on a GPU. It makes use of auto-di…☆10Aug 28, 2018Updated 7 years ago
- Code for the paper "Function-Space Learning Rates"☆24Jun 3, 2025Updated 11 months ago
- ☆21Aug 18, 2022Updated 3 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- In-silico design pipeline for evaluating protein structure diffusion models.☆31Jun 25, 2024Updated last year
- [NeurIPS 2025] Official code for "Tropical Attention: Neural Algorithmic Reasoning for Combinatorial Algorithms"☆29Oct 23, 2025Updated 6 months ago
- Tabula Rasa Tic-Tac-Toe☆10Jan 3, 2019Updated 7 years ago
- LLM sampling method for enforcing syntax adherence in generated output☆25May 31, 2023Updated 2 years ago
- ☆55Apr 11, 2023Updated 3 years ago
- Tools for studying developmental interpretability in neural networks.☆134Apr 23, 2026Updated 2 weeks ago
- Two implementations of ZeRO-1 optimizer sharding in JAX☆14Jun 11, 2023Updated 2 years ago
- This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.☆35Oct 28, 2025Updated 6 months ago
- Pruning is all you need (hopefully)☆12Sep 7, 2022Updated 3 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Code for paper "Parameter Efficient Multi-task Model Fusion with Partial Linearization"☆25Sep 13, 2024Updated last year
- Universal Neurons in GPT2 Language Models☆30May 28, 2024Updated last year
- Source code of "What can linearized neural networks actually say about generalization?☆20Oct 21, 2021Updated 4 years ago
- Code for the paper Alpha Zero in Continuous Action Space (A0C) (https://arxiv.org/pdf/1805.09613.pdf)☆15Jan 19, 2021Updated 5 years ago
- [ICLR2023] NTK-SAP: Improving neural network pruning by aligning training dynamics☆20May 1, 2023Updated 3 years ago
- Utilities for the HuggingFace transformers library☆76Jan 21, 2023Updated 3 years ago
- A formalisation of Cartesian Frames, a perspective on embedded agency, in the HOL theorem prover.☆21Dec 20, 2021Updated 4 years ago
- A Windows program to search for cellular automata patterns☆16Jan 24, 2013Updated 13 years ago
- Offline RL experiments☆15Oct 1, 2022Updated 3 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Minimum Description Length Recurrent Neural Networks☆19Jun 9, 2023Updated 2 years ago
- ☆15Jun 10, 2022Updated 3 years ago
- Code for "Just Train Twice: Improving Group Robustness without Training Group Information"☆72May 18, 2024Updated last year
- See the issue board for the current status of active and prospective projects!☆65Feb 12, 2022Updated 4 years ago
- code associated with paper "Sparse Bayesian Optimization"☆26Oct 31, 2023Updated 2 years ago
- Overlooked Factors in Concept-based Explanations: Dataset Choice, Concept Learnability, and Human Capability (CVPR 2023)☆10Mar 14, 2023Updated 3 years ago
- Computationally friendly hyper-parameter search with DP-SGD☆25Jan 7, 2025Updated last year
- PyTorch implementation of "PatchVAE: Learning Local Latent Codes for Recognition" to appear in CVPR 2020☆14Apr 9, 2020Updated 6 years ago
- Tools for generating and comparing Decorated Merge Trees, enriched persistence-based topological data descriptors.☆17Aug 27, 2022Updated 3 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Neural Fictitious Self-Play in Leduc Holdem☆11Jul 4, 2018Updated 7 years ago
- Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam☆87Jul 28, 2024Updated last year
- A WGAN-GP that utilizes a compositional pattern producing network as the generator☆11Sep 9, 2021Updated 4 years ago
- A short conceptual replication of "Prefrontal cortex as a meta-reinforcement learning system" in Jax.☆18Feb 27, 2023Updated 3 years ago
- Code for T-MARS data filtering☆35Aug 23, 2023Updated 2 years ago
- Minimal (truly) muP implementation, consistent with TP4 and TP5 papers notation☆14Jan 2, 2026Updated 4 months ago
- Experiments Notebook of "Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism"☆15Apr 30, 2025Updated last year