Comment by gavinray
1 month ago
This is stated in the original post as well, under "The Beginning of LLM Neuroanatomy?" section:
> From end-position 43 to 46, we then see solid boosts in math scores (red = good, yay). But include layer 46 or beyond, and the benefits collapse again. The hypothesis: position 47 is where a different circuit begins. Including even one step of the next recipe messes up the current recipe.
> So the ‘math organ’ has boundaries on both sides. Too few layers and you get nothing — you’ve cut into the circuit and it can’t complete its operation. Too many layers and you also get nothing — you’ve included tissue from a neighbouring circuit that doesn’t belong. Pre-training carved these structures out of the layer stack, and they only work whole. It also doesn’t translate to other tasks, as the heatmap for EQ scores doesn’t have this patch.
> This is a much more specific claim than “middle layers do reasoning.” It’s saying the reasoning cortex is organised into functional circuits: coherent multi-layer units that perform complete cognitive operations. Each circuit is an indivisible processing unit, and the sweeps seen in the heatmap is essentially discovering the boundaries of these circuits.
That's just saying there are circuits. It's not saying you get different effects by stacking the same circuit in different ways.