diff options
Diffstat (limited to 'docs/blog-jlens-frequency.md')
| -rw-r--r-- | docs/blog-jlens-frequency.md | 14 |
1 files changed, 14 insertions, 0 deletions
diff --git a/docs/blog-jlens-frequency.md b/docs/blog-jlens-frequency.md index e73a2fe..7e01de0 100644 --- a/docs/blog-jlens-frequency.md +++ b/docs/blog-jlens-frequency.md @@ -198,6 +198,20 @@ either, and its one acknowledgment of high-frequency-token trouble was in a separate method they chose not to use. Any "privileged subspace" interpretation needs a frequency control first. +We are also not alone in noticing the raw lens is distorted by token +statistics. An independent research-engineer analysis of the same paper +(willkn, "Anthropic's J-Lens: A Research Engineer's Analysis", GreaterWrong, +24 Jul 2026), working on GPT-2-medium (355M — thirty times our model), found +that the raw fitted Jacobian "misweights structural tokens (grammar, +punctuation) over semantic content" — its dominant spectral channels carry +~10x the gain of the residual pathway. Structural tokens are the high-frequency +tokens. They also found the Jacobian essentially full-rank (562-858 dimensions +for 90% of spectral variance), matching our toy-scale rank result. Their fix is +a single-parameter shrinkage regularizer (J + λI) that restores next-token +faithfulness — and Anthropic's released fitting code applies no such +regularization. Whether shrinkage also removes the frequency correlation is an +experiment we have not run yet; it is a natural next step. + ## 7. But not *only* frequency Now the twist. Correlation is not causation, so we ran a cleaner test. We made |