INDEX

Explanations

terms related to law enforcement and crime prevention organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

+#+#

-0.56

 gekomen

-0.55

 beroep

-0.53

 geïsole

-0.53

bucha

-0.52

 wikipagina

-0.51

ACIN

-0.50

SourceChecksum

-0.49

expandindo

-0.49

 trouw

-0.48

POSITIVE LOGITS

 crime

0.69

 crimes

0.61

 burglary

0.54

 Crime

0.54

 thefts

0.54

 CRIME

0.53

Crime

0.53

crime

0.51

 burglar

0.51

Theft

0.48

Activations Density 0.292%

terms related to law enforcement and crime prevention organizations

No Comments

No Known Activations