Skip to content
Global sound
The AI Alignment Podcast

The AI Alignment Podcast

The Model Explains Itself: Turning Activations Into Words

· 48 min · Season 1 Episode 2

Show notes

In this episode, AE Studio Research Director Mike Vaiana is joined by Research Scientist Keenan Pepper, to explore a new approach to model self-interpretation - teaching language models to explain their own internal activations.
They dive into Keenan’s recent paper on training lightweight adapters that transform activation vectors into soft tokens the model can interpret as language. The conversation walks through how this method improves on prior approaches like SelfIE, and how simple affine transformations can unlock surprisingly strong interpretability.
Mike and Keenan break down concrete…

Website: podcasters.spotify.com

Live, last hour: 9,887 songs on 4,733 stations in 137 countries

Discover the world through radio

More ways to discover (7)

Heard something good? Save it, or open it straight away in Spotify.

★ Artist of the week The fastest riser on the radio this week
Your song here? From € 9 per week →
Radio 538 luisteren - Live!Popular right now