Understanding Grokking via Mechanistic Interpretability
📺 Today’s recommended deep-dive video: https://www.youtube.com/watch?v=IHikLL8ULa4 Decoding the Ghost in the Machine: How Models “Grok” Through Trigonometry For months, researchers were baffled by neural networks that suddenly learned to generalize after long periods of stagnation. This deep dive into mechanistic…