Ablation is Not Enough to Emulate DPO: How Neuron Dynamics Drive Toxicity Reduction
Paper
•
2411.06424
•
Published
•
5
YY
yy0514
AI & ML interests
None yet
Recent Activity
authored
a paper
about 1 month ago
Can sparse autoencoders be used to decompose and interpret steering
vectors?
commented
a paper
about 1 month ago
Can sparse autoencoders be used to decompose and interpret steering
vectors?
upvoted
a
paper
about 2 months ago
Ablation is Not Enough to Emulate DPO: How Neuron Dynamics Drive
Toxicity Reduction
Organizations
None yet