6 citations · 6 across the 4 of their papers we have counts for
4 papers
Obfuscated Activations Bypass LLM Latent-Space Defenses
Luke Bailey, Alex Serrano, Abhay Sheshadri +7
Recent latent-space monitoring techniques have shown promise as defenses against LLM attacks. These defenses act as scanners that seek to detect harmful activations before they lea…
Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
Dan Braun, Jordan Taylor, Nicholas Goldowsky-Dill +1
Identifying the features learned by neural networks is a core challenge in mechanistic interpretability. Sparse autoencoders (SAEs), which learn a sparse, overcomplete dictionary t…
An introduction to graphical tensor notation for mechanistic interpretability
Jordan K. Taylor
Graphical tensor notation is a simple way of denoting linear operations on tensors, originating from physics. Modern deep learning consists almost entirely of operations on or betw…
Wavefunction branching: when you can't tell pure states from mixed states
Jordan K. Taylor, Ian P. McCulloch
We propose a definition of wavefunction "branchings": quantum superpositions which can't be feasibly distinguished from the corresponding mixed state, even under time evolution. Ou…