diff options
Diffstat (limited to 'docs/blog-jlens-frequency.md')
| -rw-r--r-- | docs/blog-jlens-frequency.md | 10 |
1 files changed, 5 insertions, 5 deletions
diff --git a/docs/blog-jlens-frequency.md b/docs/blog-jlens-frequency.md index 8ab2e46..0d51c8d 100644 --- a/docs/blog-jlens-frequency.md +++ b/docs/blog-jlens-frequency.md @@ -18,11 +18,11 @@ into two separable parts. Half lives in the static geometry of the model's word-scoring matrix — baked into the lens by definition, so any user inherits it. A smaller, layer-dependent part lives in what the layers themselves do, and vanishes at the final layer. A frequency-matched synthetic pair shows the lens -also carries genuine structure signal (with a caveat we're resolving), and a -causal test found the demotion effect is small under loss reweighting. We are -**not** claiming the J-space doesn't exist. We're claiming that any -"privileged subspace" interpretation needs a frequency control first. The full -story — numbers, mistakes, and all — is below. +also carries genuine structure signal (confirmed by a clean-boundary control at +~1.3x), and a causal test found the demotion effect is small under loss +reweighting. We are **not** claiming the J-space doesn't exist. We're claiming +that any "privileged subspace" interpretation needs a frequency control first. +The full story — numbers, mistakes, and all — is below. --- |