Re:We Found an Neuron in GPT-2
by theptip on Thursday February 16, 2023 @08:32PM
(#34829488)
I think this would be a valid objection if they stopped there.
But then: “ Testing the neuron on a larger dataset”
If I follow correctly, they test a bunch of different completions that contain “an”. So they are not just detecting the bigram “an apple”, but the common activation among a bunch of “an X” activations where X is completely different.
But then: “ Testing the neuron on a larger dataset”
If I follow correctly, they test a bunch of different completions that contain “an”. So they are not just detecting the bigram “an apple”, but the common activation among a bunch of “an X” activations where X is completely different.