INDEX

Explanations

criteria related to age and eligibility for participation in studies or programs

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

adults aged 18 years and older

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 GenerationType

-0.47

BagLayout

-0.39

yelitis

-0.38

 lyck

-0.36

 overflow

-0.36

computation

-0.35

 kasarigan

-0.35

geddon

-0.35

adpleegd

-0.35

getCause

-0.35

POSITIVE LOGITS

 adult

0.77

Adult

0.71

 Adult

0.69

 adulte

0.68

 adults

0.66

 adulthood

0.65

adult

0.63

Adults

0.60

 adultes

0.60

 adulta

0.60

Activations Density 0.022%

criteria related to age and eligibility for participation in studies or programs

adults aged 18 years and older

No Comments

No Known Activations