summaryrefslogtreecommitdiff
path: root/docs/blog-jlens-frequency.md
diff options
context:
space:
mode:
Diffstat (limited to 'docs/blog-jlens-frequency.md')
-rw-r--r--docs/blog-jlens-frequency.md6
1 files changed, 6 insertions, 0 deletions
diff --git a/docs/blog-jlens-frequency.md b/docs/blog-jlens-frequency.md
index dec1edf..8ab2e46 100644
--- a/docs/blog-jlens-frequency.md
+++ b/docs/blog-jlens-frequency.md
@@ -385,6 +385,12 @@ regime where Anthropic's claims live) with proper statistical power, and to run
the occupancy test their capacity claim is actually about. That's the next
post.
+The learned-geometry finding makes one piece of that cheap and decisive: if
+the W_U row-norm anti-correlation is a general property of softmax-output
+models trained on Zipfian data, it should appear in GPT-2's unembedding matrix
+directly — no Jacobian computation at all. One line of code at scale, and it
+either generalizes or it doesn't.
+
## 11. How to reproduce everything
All code, data-prep scripts, experiment scripts, tests, and this analysis live