Periodic Labs' Rohan Pandey jokes that backpropagation is the ultimate interpretability researcher, easily identifying and steering neuron behaviors
The joke critiques the complexity of modern mechanistic interpretability.
@aryaman2020 wow my interp take has been aryaman approved lfg
Aryaman Arora@aryaman2020true
@ChengleiSi @aryaman2020 truly the goat
CLS@ChengleiSi@khoomeik my favorite interp researcher is @aryaman2020, he can identify neurons responsible for any behavior by just eyeballing the matrices
#442CLS@CHENGLEISI@khoomeik my favorite interp researcher is @aryaman2020, he can identify neurons responsible for any behavior by just eyeballing the matrices
Rohan Pandey@khoomeikmy favorite interp researcher can identify neurons responsible for any behavior and provide steering vectors for them her name is backprop and her steering vectors are just gradients
@aryaman2020 related - I’m always curious why interpretability people design a cool new parameter efficient finetuning family like steering vectors and then choose not to optimize by gradient descent
Aryaman Arora@aryaman2020true
#678Aryaman Arora@ARYAMAN2020true
Rohan Pandey@khoomeikmy favorite interp researcher can identify neurons responsible for any behavior and provide steering vectors for them her name is backprop and her steering vectors are just gradients
@khoomeik im a gradients guy https://arxiv.org/abs/2604.07615
Rohan Pandey@khoomeik@aryaman2020 wow my interp take has been aryaman approved lfg