INDEX

Explanations

mentions of advertising in apps

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

np_acts-logits-general · gemini-2.0-flash

advertising words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

曖昧さ回避

-0.53

BeginInit

-0.52

 ddelweddau

-0.51

CloseOperation

-0.49

Scénario

-0.49

homonymie

-0.48

AndEndTag

-0.48

 smtplib

-0.47

oa̍t

-0.47

_{+}

-0.47

POSITIVE LOGITS

ad

1.02

ads

1.01

Ad

0.94

Ads

0.88

 Display

0.88

 advertisers

0.88

 display

0.87

Ad

0.86

 placements

0.85

 advertiser

0.83

Activations Density 0.154%

mentions of advertising in apps

advertisements

advertising words

No Comments

No Known Activations