Saltar al contenido
onsuggest
Iniciar sesión
Artículo en

J-lens preferentially reads from coordinate-aligned subspaces

Fuente: LessWrong ·

Note: I only test on Gemma-4-31B, which contains the spaces I've been studying in this earlier post . This is a shorter post, with just a few observations potentially relevant to those working on the J-lens work. The main observations here are: In Gemma-4, there are two relatively small subspaces that account the majority of the J-lens readout. These are both coordinate-aligned subspaces. That means we can take a hidden state, mask out all coordinates except both these ~600 coordinate groups, and it will capture ~80-95% of the J-lens readout. These spaces are not built to capture J-lens contri

¿Qué es J-lens preferentially reads from coordinate-aligned subspaces?

J-lens preferentially reads from coordinate-aligned subspaces is a artículo discovery curated from LessWrong. Note: I only test on Gemma-4-31B, which contains the spaces I've been studying in this earlier post . This is a shorter post, with just a few observations potentially relevant to t

¿Cómo puedo acceder o experimentarlo?

You can experience this content directly on its original host (LessWrong) by clicking the "Open Original" button.

¿De dónde proviene este contenido?

Curated from LessWrong by the OnSuggest team to surface the most interesting and serendipitous content on the web.

Artículo · Cultura e ideas

Dems won the midterms. How should they work with Trump?

Just days after big wins in the midterms, Democrats are celebrating historic victories. But what can we actually learn from these wins? David Axelrod is a Democratic strategist and the man behind Barack Obama’s two presidential victories. He’s not a senior political commentator at CNN. He’s spent decades figuring out how Democrats can win. On […]

Artículo · Cultura e ideas

JD Vance’s bad week gets worse

This story appeared in Today, Explained, a daily newsletter that helps you understand the most compelling news and stories of the day. Subscribe here. Hi readers, happy Friday! What a week, right? My colleague Caitlin Dewey has spent the last two days unpacking some of the midterm results and their implications for you, and there will be lots […]

Atajos de teclado

Descubrimiento anterior
←P
Siguiente descubrimiento
→N
Me gusta
L
No es para mí
X
Guardar
S
Mostrar esta ayuda
?
Cerrar
Esc

Los atajos funcionan en la página de descubrimientos.