OCR feature fragility
Enter a reference text and its OCR version. Each reference token is encoded by a historical NER model (BERT, en/fr/de) and a TopK sparse autoencoder (2,048 features, 32 active per token). A feature is lost when its activation on the aligned OCR token falls below half of the reference activation. Colour shows the share of a token's active features that were lost; unchanged tokens next to an edit can lose features too (collateral damage).
Tokens
Most frequently lost features
Examples (the last two are real chunks where a correctly transcribed entity still changes label)
| Reference text | OCR text | NER block the SAE reads |
|---|