INDEX

Explanations

content related to violence and content ratings

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

Content ratings and offensive language

np_acts-logits-general · gemini-2.0-flash

R rated or profanity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WithIOException

-0.72

]='\

-0.71

featureID

-0.65

DockStyle

-0.63

SOUNDBITE

-0.62

 ilusión

-0.59

__':

-0.57

 createSprite

-0.56

__':

-0.56

==""){

-0.54

POSITIVE LOGITS

 vulgar

0.96

 swearing

0.93

 explicit

0.91

 obscene

0.91

 swear

0.90

 NSFW

0.89

 nudity

0.86

 prof

0.85

 obsc

0.84

 swears

0.84

Activations Density 0.208%

content related to violence and content ratings

Content ratings and offensive language

R rated or profanity

No Comments

No Known Activations