Across ten pretrained GPT-2 and Pythia checkpoints from 70M to 2.8B parameters, routing remains approximately blind to read norm: the quiet-read blind-mass ratio stays between one and two, and the content share through the quiet band is broadly flat with scale.

Across ten pretrained GPT-2 and Pythia checkpoints from 70M to 2.8B parameters, routing remains approximately blind to read norm: the quiet-read blind-mass ratio stays between one and two, and the content share through the quiet band is broadly flat with scale. · CiteArk

Measurement results

0/70 assessed

0 supported0 disputed or conflicting70 not assessed

The complete result group stays with its claim. Assessed rows come first; their judgments do not replace the whole-claim conclusion. Expand a row for conditions, sources, and evidence history.

Each row is a measurement with its reported value, latest available observation, and cumulative evidence state.
Metric and conditions	Reported	Latest observation	Evidence judgment
model: gpt2	124 millions of parameters	—	Not assessed
model: gpt2	12 count	—	Not assessed
model: gpt2	12 count	—	Not assessed
model: gpt2	0.364 fraction	—	Not assessed
model: gpt2	0.144 ratio	—	Not assessed
model: gpt2	1.03 ratio	—	Not assessed
model: gpt2	0.258 fraction	—	Not assessed
model: gpt2-medium	355 millions of parameters	—	Not assessed
model: gpt2-medium	24 count	—	Not assessed
model: gpt2-medium	16 count	—	Not assessed
model: gpt2-medium	0.388 fraction	—	Not assessed
model: gpt2-medium	0.092 ratio	—	Not assessed

Across ten pretrained GPT-2 and Pythia checkpoints from 70M to 2.8B parameters, routing remains approximately blind to read norm: the quiet-read blind-mass ratio stays between one and two, and the content share through the quiet band is broadly flat with scale.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results