INDEX

Explanations

terms associated with sex work and related themes

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mybatisplus

-0.62

RTGC

-0.55

DrawerToggle

-0.54

IntoConstraints

-0.53

dymyr

-0.53

viewDidLoad

-0.51

 casse

-0.50

ⓧ

-0.50

 fondant

-0.49

 zdan

-0.49

POSITIVE LOGITS

 prostitution

0.96

 prostitu

0.94

 prostitute

0.91

 prostitutes

0.88

娼

0.54

 sexuales

0.49

pim

0.48

Porn

0.47

Sex

0.45

 porn

0.45

Activations Density 0.008%

terms associated with sex work and related themes

No Comments

No Known Activations