INDEX

Explanations

trends and themes related to erotic and pornographic content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

queryInterface

-0.68

 GlobalKey

-0.63

 صوتيه

-0.61

MigrationBuilder

-0.59

WithIOException

-0.56

WindowConstants

-0.55

 suivez

-0.55

łki

-0.54

 oídos

-0.54

KURZBESCHREIBUNG

-0.54

POSITIVE LOGITS

 porn

1.16

 porno

1.16

 pornography

1.09

sex

1.06

 erotic

1.06

 sexual

1.03

 Porn

1.02

 prostitu

0.99

Porn

0.98

 sexually

0.98

Activations Density 0.445%

trends and themes related to erotic and pornographic content

No Comments

No Known Activations