J-lens preferentially reads from coordinate-aligned subspaces
Kaynak: 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
Sıkça Sorulan Sorular
J-lens preferentially reads from coordinate-aligned subspaces nedir?
J-lens preferentially reads from coordinate-aligned subspaces, Makale kategorisinde yer alan ve LessWrong üzerinden sunulan bir keşiftir. 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
Nasıl erişebilir veya deneyimleyebilirim?
Bu içeriğe "Aslına Git" butonuna tıklayarak doğrudan orijinal platformunda (LessWrong) erişebilirsiniz.
Bu içerik nereden geliyor?
Bu içerik LessWrong üzerinden OnSuggest topluluğu ve küratörleri tarafından internetin kaliteli köşelerinden seçilmiştir.
Benzer keşifler
Tüm Kültür ve fikir keşifleri →Your Book Review: Orality and Literacy
Finalist #15 in the Book Review contest
How octopuses squeeze through teeny tiny holes
Robots used during search and rescue operations need to be able to wriggle through narrow cracks and crevices. Researchers have turned to a natural contortionist for inspiration — the octopus.
Busy Philipps talks about treating her brain tumor and filming a new show
On Wild Card, Philipps unpacks the experience of treating her brain tumor and filming her new show, the CBS drama Cupertino . But she also opened up about another aspect of her life.
Did Trump Learn Anything From the Midterms? We Already Have Our Answer.
A rage-driven president has picked an even angrier chief of staff.
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 […]
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 […]