No, the closest analogue of comparing text snippets is staring at image completions, which is not nearly as informative as being able to go neuron-by-neuron or layer-by-layer and get a sense of the concepts at each level.
No, the closest analogue of comparing text snippets is staring at image completions, which is not nearly as informative as being able to go neuron-by-neuron or layer-by-layer and get a sense of the concepts at each level.