factual

Larger models share abstractions across languages instead of separating them

Counterintuitively, larger models share more representation across languages and modalities in an abstract space rather than separating concepts into distinct neurons; despite having more capacity to separate things, bigger models pull on better, shared abstractions—e.g. the same neural pattern represents the Golden Gate Bridge as text or image, and notions like large/small or hot/cold are shared across languages.

factualpending

Speaker

Trenton Bricken

Evidence Quote

“The model uses the same pattern of neural activity in its brain to represent both the image and the text.”

Source

Is RL + LLMs enough for AGI? — Sholto Douglas & Trenton Bricken— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:28:51 AM

Your notes

Loading notes...