INDEX

Explanations

terms and concepts related to crime and criminal activity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ILayout

-0.84

 للاسماء

-0.75

 дописавши

-0.71

LookAnd

-0.69

parsedMessage

-0.67

 wünscht

-0.66

 Wrang

-0.65

 ArrayAdapter

-0.64

iphery

-0.64

 سكانية

-0.63

POSITIVE LOGITS

 crime

1.76

 crimes

1.69

 Crime

1.67

 Crimes

1.55

Crime

1.52

 CRIME

1.47

crime

1.36

 criminal

1.27

crimes

1.26

 crimen

1.14

Activations Density 0.199%

terms and concepts related to crime and criminal activity

No Comments

No Known Activations