Finite experiments certify integrated information in 4-5 unit networks
Recurrent and feed-forward networks with identical behavior carry different φ values and are separable by internal recordings.
Stories per day · 30 days
2 stories, newest first · one card per story
Stories tagged #ai-interpretability
Activation inversion metamodels scale interpretation of residual stream directions
MAEMs generate text exemplars that activate supplied residual stream directions better than corpus search or autoencoders.