openai/grok
Some data may be outdated — see provenance labels.
None observed · 2026-09-24
Health v2 · maintenance only
10/100
- Activity 0
- Release rhythm 35
- Longevity 100
Flags: no_releases archived
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-22. Adoption (stars, forks) is never an input.
- gap_med: n/a
- age_days: 2018
- days_rel: n/a
- days_push: 946
- n_releases_24m: 0
Adoption not part of the score
4259 stars · 589 forks observed · 2026-09-24
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded
Research code accompanying the paper 'Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets' from OpenAI. It provides training scripts to reproduce grokking curve experiments on small algorithmic datasets.
Use cases
- reproduce grokking experiments from the paper
- study delayed generalization in neural networks
- train models on small algorithmic datasets
- explore overfitting vs generalization dynamics
- research deep learning generalization phenomena
When to choose
- you want to reproduce or extend the grokking paper's experiments
- you are researching generalization dynamics in small-scale neural network training
When to avoid
- you need a production machine learning framework
- you want a maintained tool with active releases
- you need training on large real-world datasets
Facets
library · maturity experimental
machine-learning deep-learning machine-learning deep-learning python grokking research-code generalization overfitting academic-paper research
1 source
- readme: https://github.com/openai/grok · fetched 2026-09-24 · 019344cffbdd
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| openai/grok | main | 10 |
For agents
Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem