Author name: Gaofei Shen, Martijn Bentum, Tom Lentz, Afra Alishahi, Grzegorz Chrupa{\l}a

arXiv:2605.00607v1 Announce Type: new
Abstract: Probing is widely used to study which features can be decoded from language model representations. However, the common decoding probe approach has two limitations that we aim to solve with our new encodi…