INDEX

Explanations

quantitative data related to health outcomes and participant statistics in studies

oai_token-act-pair · gpt-4o-mini Triggered by @bot

preceding "rate" or "prevalence"

np_acts-logits-general · gemini-2.0-flash

statistical rates and prevalence

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PerformLayout

-0.48

ביוגרפיה

-0.47

 venons

-0.46

 صوتيه

-0.45

 endblock

-0.44

 души

-0.44

mitian

-0.44

Handlung

-0.44

 esterno

-0.44

џ

-0.44

POSITIVE LOGITS

 rate

2.27

 rates

2.06

 Rate

1.94

 RATE

1.80

Rate

1.78

rate

1.78

 Rates

1.76

 RATES

1.60

Rates

1.57

rates

1.56

Activations Density 1.074%

quantitative data related to health outcomes and participant statistics in studies

preceding "rate" or "prevalence"

statistical rates and prevalence

No Comments

No Known Activations