Ah, that makes sense. So, we consider two hidden layers more as "memory" or "buf...

		Fripplebubby on July 1, 2024 \| parent \| context \| favorite \| on: My Python code is a neural network Ah, that makes sense. So, we consider two hidden layers more as "memory" or "buffers", and actually the rule is implemented in just one layer, at least for a single token.