INDEX

Explanations

quantitative data or statistics related to demographics, programs, or resources

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

Large numerical values

np_acts-logits-general · gemini-2.0-flash

numerical quantities and scales

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

 pouvoirs

-0.57

setFlags

-0.54

 للمعارف

-0.52

 NSError

-0.52

 kasarigan

-0.50

 besoins

-0.50

))))

-0.49

RunWith

-0.49

))),

-0.48

atiles

-0.48

POSITIVE LOGITS

 million

1.28

 thousand

1.26

thousand

0.97

 thousands

0.97

 billion

0.96

 MILLION

0.95

 hundred

0.93

million

0.93

 THOUS

0.90

 different

0.87

Activations Density 0.354%

quantitative data or statistics related to demographics, programs, or resources

Large numerical values

numerical quantities and scales

No Comments

No Known Activations