enjoying the new global workspace anthropic paper - especially using the Jacobian lens to provide readout interpretations of prints shown at last month CVPR
pleased to be showing new screenprints at @CVPRConf this weekend. these use mechanistic interpretability techniques to highlight features shared across a wide family of vision models
saxophone print + top-150 SigLIP image probe
though mknn model agreement (a la platonic representation hypothesis) is not part of the test time compute process, it climbs naturally as the as the optimization evolves
unsure how AI interprets this print? treating the image as a linear probe on your favorite vision model and scraping a diverse dataset for maximum activations provides a coherent suggestion.
