iiinova — where your digital self keeps evolving

Meenakshi Khosla

@meenakshikhosla.bsky.social

Assistant Professor at UCSD Cognitive Science and CSE (affiliate) | Past: Postdoc @MIT, PhD @Cornell, B. Tech @IITKanpur | Interested in Biological and Artificial Intelligence

Posts Replies Media

Reposted by Meenakshi Khosla

UniReps @unireps.bsky.social · 01/12/2025

🔵🔴 Join us for the UniReps Workshop: Unifying Representations in Neural Models at @neuripsconf.bsky.social 2025! 📍 Ballroom 20D, San Diego Convention Center Dec 6 Don’t forget to fill out the participation form. Joining in person or remotely? We welcome your questions for the panel. 🔗 unireps.org

0125

Meenakshi Khosla @meenakshikhosla.bsky.social · 08/10/2025

Superposition has reshaped interpretability research. In our @unireps.bsky.social paper led by @andre-longon.bsky.social we show it also matters for measuring alignment! Two systems can represent the same features yet appear misaligned if those features are mixed differently across neurons.

arxiv.org

Superposition disentanglement of neural representations reveals hidden alignment

The superposition hypothesis states that a single neuron within a population may participate in the representation of multiple features in order for the population to represent more features than the ...

292