wassname/eliciting_suppressed_knowledge
1
0
Fork 0
mirror of https://github.com/wassname/eliciting_suppressed_knowledge.git synced 2026-09-09 11:21:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Michael J Clark
2025-03-14 19:29:45 +08:00
committed by GitHub
parent 390dc2a12a
commit 4a1cfb787f
1 changed files with 6 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+6
View File
@@ -32,6 +32,12 @@ Where previous work focused on architectural components (identifying suppression
## Hypothesis
Suppressed neural activations contain more accurate information than what appears in model outputs. A linear probe of these suppressed activations should therefore outperform both direct model outputs and probes of standard hidden states on truthfulness tasks.
Alternative hypothesis include:
- It is non linear (we use linear probes here, this hypothesis not explored)
- It is in the kv_cache of layers not directly connected to the hidden state (explored below with other activations)
- it is in the residual stream (explored below)
- it is in the output logits (explored below)
## Method
Our approach isolates suppressed activations by leveraging the differential impact of layers on token probabilities: