I have to dispute the idea that “less neurons” = “more human-readable”. If the fewer neurons are performing a more complex task it won’t necessarily be easier to interpret.
Definately. The lower the neuron vs ‘concepts’ ratio is, the more superposition required to represent everything. That said with the continuous function nature of LNNs these seem to be the wrong abstraction for language. Image models? Maybe. Audio models? Definately. Tokens and/or semantic data? That doesnt seeem practical.
I have to dispute the idea that “less neurons” = “more human-readable”. If the fewer neurons are performing a more complex task it won’t necessarily be easier to interpret.
Definately. The lower the neuron vs ‘concepts’ ratio is, the more superposition required to represent everything. That said with the continuous function nature of LNNs these seem to be the wrong abstraction for language. Image models? Maybe. Audio models? Definately. Tokens and/or semantic data? That doesnt seeem practical.