Zayden-Jung/exp-model-parameter-similarity
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Quantify adjacent-layer head influence concentration on CPU

Browse Source
This commit is contained in:
Codex Bot
2026-11-10 22:38:15 +08:00
parent cd260a2483
commit 098ea8650c
136 changed files with 24841 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+9
View File
@@ -42,3 +42,12 @@ Full resolved versions and run provenance accompany each result. See the SOP for
## CPU block activation measurements
See [measurement definitions](activation/README.md) and [observed activation report](results/block-activation/REPORT.md) for all 24 layers, contiguous output-channel blocks, exact/near-zero rates and output energy concentration. This is an observational SiLU-gated study, not a pruning or reuse quality claim.
## Adjacent-layer head influence concentration
The CPU study measures all 23 adjacent transitions, observation-wise effective
head counts and Q/K/V influence shares, with equal-size weak/strong/random joint
removal controls. See [definitions and reproduction](dominance/README.md),
[fixed protocol](dominance/PROTOCOL.md), and [measured report](results/head-dominance/REPORT.md).
These are descriptive intervention effects, not additive contribution probabilities
or validated final-LM pruning gains.