RSS

Magdalena Wache

Karma: 566

The Lo­cal In­ter­ac­tion Ba­sis: Iden­ti­fy­ing Com­pu­ta­tion­ally-Rele­vant and Sparsely In­ter­act­ing Fea­tures in Neu­ral Networks

Lucius Bushnaq, jake_mendel, Dan Braun, StefanHex, Nicholas Goldowsky-Dill, Kaarel, Avery, Joern Stoehler, debrevitatevitae, Magdalena Wache and Marius Hobbhahn
May 20, 2024, 5:53 PM
108 points
4 comments3 min readLW link

In­ter­pretabil­ity Ex­ter­nal­ities Case Study—Hun­gry Hun­gry Hippos

Magdalena WacheSep 20, 2023, 2:42 PM
64 points
22 comments2 min readLW link

Tech­ni­cal AI Safety Re­search Land­scape [Slides]

Magdalena WacheSep 18, 2023, 1:56 PM
49 points
2 comments4 min readLW link

AI Safety Europe Re­treat 2023 Retrospective

Magdalena WacheApr 14, 2023, 9:05 AM
43 points
0 comments2 min readLW link

Finite Fac­tored Sets in Pictures

Magdalena WacheDec 11, 2022, 6:49 PM
183 points
35 comments12 min readLW link