AI ALIGNMENT FORUM
AF

Wikitags

Grokking (ML)

Edited by Morpheus last updated 29th Feb 2024

A Phenomenon in machine learning where a machine learning model generalizes to a test set only long after it achieved perfect loss on the training set.

Subscribe
Subscribe
Discussion0
Discussion0
Posts tagged Grokking (ML)
106A Mechanistic Interpretability Analysis of Grokking
Neel Nanda, Tom Lieberum
3y
18
50QAPR 5: grokking is maybe not *that* big a deal?
Quintin Pope
2y
8
50Explaining grokking through circuit efficiency
Vikrant Varma, Rohin Shah
2y
10
16Paper+Summary: OMNIGROK: GROKKING BEYOND ALGORITHMIC DATA
Marius Hobbhahn
3y
0
12Mesa-Optimizers via Grokking
orthonormal
3y
2
13An interactive introduction to grokking and mechanistic interpretability
Adam Pearce, Asma Ghandeharioun
2y
0
15AXRP Episode 29 - Science of Deep Learning with Vikrant Varma
DanielFilan
1y
1
Add Posts