You may never have heard of modular arithmetic, but you use it every day without the slightest difficulty. In this system, numbers wrap around when they reach a certain size called the modulus; it is ...
Code for the the paper "Emergence in non-neural models: grokking modular arithmetic via average gradient outer product" which can be found here.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results