alt Hacker NewsIt's unclear from the doc: by `activations` do they mean the connections between neurons? Since a network has multiple layers, are these activations the concatenated outputs of all of the layers? Or just the final layer before the softmax?
It's unclear from the doc: by `activations` do they mean the connections between neurons? Since a network has multiple layers, are these activations the concatenated outputs of all of the layers? Or just the final layer before the softmax?
The open releases just cherry-pick a single layer (chosen for the right "depth" of thinking, not too close to either the input or the final answer) and analyze that.