For modular multiplication at each reported modulus (79, 97, and 127), EGD groks after only a few epochs and earlier than all plotted alternatives, which remain on long plateaus before eventually grokking. · CiteArk
For modular multiplication at each reported modulus (79, 97, and 127), EGD groks after only a few epochs and earlier than all plotted alternatives, which remain on long plateaus before eventually grokking.
来源：paper:PDF pp. 2 and 10, Figure 2 and Section 5.2
