You are wildly overestimating how much computation in superposition is possible.
The bottleneck for comp-in-sup is not fitting the info into the neurons, but fitting the circuits into the weights.
I think your circuit depth calculations assume that each circuit get’s to use the entire weight matrix at each step. That’s not how this works.
Despite this I over all agree with your picture (but disagree with the implications). I expect may shallow circuits. However you seem to expect that most circuits are mostly end to end, maybe the network picks one or computes all and choses which output to use at the end? I expect the circuits to be much shorter than that, and much more composable. I.e. there are many circuits in cereal, and each output determine which one to trigger next.
I think this structure can be very agentic, when large enough.
You are wildly overestimating how much computation in superposition is possible.
The bottleneck for comp-in-sup is not fitting the info into the neurons, but fitting the circuits into the weights.
I think your circuit depth calculations assume that each circuit get’s to use the entire weight matrix at each step. That’s not how this works.
Despite this I over all agree with your picture (but disagree with the implications). I expect may shallow circuits. However you seem to expect that most circuits are mostly end to end, maybe the network picks one or computes all and choses which output to use at the end? I expect the circuits to be much shorter than that, and much more composable. I.e. there are many circuits in cereal, and each output determine which one to trigger next.
I think this structure can be very agentic, when large enough.