“amount that layer 52 looks at the output of layer 18” does unfortunately seem like a less interpretable quantity than attention scores between parts of the context / output, where we get to have an intuitive sense of what the tokens mean just by reading them.
“amount that layer 52 looks at the output of layer 18” does unfortunately seem like a less interpretable quantity than attention scores between parts of the context / output, where we get to have an intuitive sense of what the tokens mean just by reading them.