paperarXivTrust 82 · PrimaryPublished 1mo agoLive · 2mo ago
Grokking in small transformers
When and why tiny models suddenly generalize long after overfitting.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via unknownWhy small models are having a moment →
- LinkedLinked via unknownBuild your first transformer from scratch →
- PossiblePossibly related (embedding) · 46%Scaling works. These researchers are betting billions it isn't enough - Transformer | Substack →
- FuzzySimilar title/name (fuzzy) · 87%lucidrains/x-transformers →
“Fuzzy title match (0.94): “Grokking in small transformers” ≈ “lucidrains/x-transformers””
- FuzzySimilar title/name (fuzzy) · 84%huggingface/transformers →
“Fuzzy title match (0.92): “Grokking in small transformers” ≈ “huggingface/transformers””