wassname/eliciting_suppressed_knowledge
1
0
Fork 0
mirror of https://github.com/wassname/eliciting_suppressed_knowledge.git synced 2026-09-10 12:00:37 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
wassname (Michael J Clark)
2025-05-06 06:31:17 +08:00
committed by GitHub
parent af8a313a7e
commit cb831ece87
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -89,7 +89,7 @@ top reduction for each data type
The highest-performing probe was on the final layer's suppressed activations (`supressed_hs`), following by filtering out high magnitudes (to remove activation sinks). This supports the hypothesis that the final "residual sharpening" stage specifically suppresses certain information pathways.
The highest-performing probe was on the final layer's suppressed activations (`supressed_hs`), following by filtering out high magnitudes (to remove [activation sinks](https://arxiv.org/abs/2410.10781)). This supports the hypothesis that the final "residual sharpening" stage specifically suppresses certain information pathways.
## Remaining Questions