Gated SAEs decouple which features to use from how large their activations should be, applying the L1 penalty only to selection and thereby eliminating shrinkage while halving the number of firing features needed for good fidelity.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
method 1polarities
use method 1representative citing papers
Poetic jailbreaks succeed because they induce distinct attention patterns in LLMs that are independent of harmful-content detection, not because models fail to recognize literary formatting.
citing papers explorer
-
Improving Dictionary Learning with Gated Sparse Autoencoders
Gated SAEs decouple which features to use from how large their activations should be, applying the L1 penalty only to selection and thereby eliminating shrinkage while halving the number of firing features needed for good fidelity.
-
Metaphor Is Not All Attention Needs
Poetic jailbreaks succeed because they induce distinct attention patterns in LLMs that are independent of harmful-content detection, not because models fail to recognize literary formatting.