A Mechanistic Interpretability Analysis of Grokking (alignmentforum.org) 1 points by poga 3y ago ↗ HN
[–] poga 3y ago ↗ related:Grokking: Generalization beyond overfitting on small algorithmic datasets https://mathai-iclr.github.io/papers/papers/MATHAI_29_paper....
1 comment
[ 3.0 ms ] story [ 15.8 ms ] threadGrokking: Generalization beyond overfitting on small algorithmic datasets https://mathai-iclr.github.io/papers/papers/MATHAI_29_paper....