Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
VGGSound
anchor
Findings
IC-148
Language models represent semantically equivalent inputs from different data types (languages, code, images, audio) close together in intermediate layers, with the shared space scaffolded by the model's dominant language
[eval]
IC-149
Intervening in the shared representation space using the dominant language (English) predictably changes model outputs for other data types, demonstrating the space is causally used rather than a vestigial byproduct
[eval]
IC-981
ImageBind's indirect alignment through images degrades zero-shot performance on non-visual modalities and prevents emergent cross-modal retrieval
[eval]