Datasets Determine How Difficult Transformers Are to Interpret

Written by

in

Two Goodfire studies suggest that Transformer neurons are more interpretable than previously thought; pruning the activations of the weakest 92% of MoE neurons increased loss by only 2.9%. Neurons can be broken down into distinct computational functions and assigned natural-language explanations that predict their behavior, but whether those explanations transfer to lab models with undisclosed architectures remains uncertain.

Source:LessWrong · Read the original

Comments

Leave a Reply

Your email address will not be published. Required fields are marked *