Can sparse autoencoders be used to decompose and interpret steering vectors?
Paper
•
2411.08790
•
Published
•
8
YY
yy0514
AI & ML interests
None yet
Recent Activity
authored
a paper
about 2 months ago
Can sparse autoencoders be used to decompose and interpret steering
vectors?
commented
a paper
about 2 months 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
yy0514's activity
authored
a
paper
about 2 months ago
commented
a
paper
about 2 months ago
upvoted
a
paper
about 2 months ago
commented
a
paper
about 2 months ago
commented
a
paper
5 months ago
authored
a
paper
5 months ago
updated
7
models
11 months ago
yy0514/llama2-7b-chat-qlora-lek-train-for-medmcqa-dev-onego-full-4-epochs
Updated
yy0514/llama2-7b-chat-qlora-lek-train-for-medmcqa-dev-full-4-epochs
Updated
•
2
yy0514/llama2-7b-chat-qlora-lek-train-for-medmcqa-dev-three-quarters-4-epochs
Updated
•
3
yy0514/llama2-7b-chat-qlora-lek-train-for-medmcqa-dev-half-4-epochs
Updated
•
2
yy0514/llama2-7b-chat-qlora-lek-train-for-medmcqa-dev-a-quarter-4-epochs
Updated
•
2
yy0514/llama2-7b-chat-qlora-lek-train-for-medmcqa-dev-a-quarter-3-epochs
Updated
•
2
yy0514/llama2-7b-chat-qlora-lek-train-for-medqa-2-epochs
Updated
updated
7
models
about 1 year ago
yy0514/bert-lek-full-train-4epochs-run2
Multiple Choice
•
Updated
•
4
yy0514/llama2-7b-chat-qlora-lek-train-4-epochs-run2
Updated
yy0514/bert-lek-full-train-4epochs
Multiple Choice
•
Updated
•
4
yy0514/roberta-lek-full-train-4epochs
Multiple Choice
•
Updated
•
48
yy0514/llama2-7b-chat-qlora-lek-train-4-epochs-new
Updated
yy0514/deberta-v3-lek-full-train-4epochs
Multiple Choice
•
Updated
•
4
yy0514/llama2-7b-qlora-lek-train-4-epochs
Updated