Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Can LLMs learn from a single example?. Parent comment
Drop a set of neurons and there’s no change? Probably doesn’t contain the “sky color” concept.
Drop a set of neurons and the model freaks out, definitely conceptual neurons.
Rinse and repeat to find the distilled pattern across all the neurons.
You could train an LLM against the neuron graph to do this for you.
There are no comments on this comment yet.
Drop a set of neurons and there’s no change? Probably doesn’t contain the “sky color” concept.
Drop a set of neurons and the model freaks out, definitely conceptual neurons.
Rinse and repeat to find the distilled pattern across all the neurons.
You could train an LLM against the neuron graph to do this for you.