INDEX

Explanations

terms associated with sexual violence and abuse

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

 Lázaro

-0.59

 surla

-0.58

ichten

-0.57

baiki

-0.56

 متحده

-0.54

 optimis

-0.54

atikan

-0.53

 facie

-0.53

GLint

-0.52

ढ

-0.52

POSITIVE LOGITS

 abuse

1.25

 abused

1.12

 Abuse

1.09

abuse

1.07

 rape

1.07

Abuse

1.07

 abus

1.04

 raped

0.98

 abusive

0.97

 abuses

0.97

Activations Density 0.414%

terms associated with sexual violence and abuse

No Comments

No Known Activations