INDEX

Explanations

references to law enforcement and police activity

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

MethodManager

-0.72

tagHelperRunner

-0.69

MemoryWarning

-0.69

ftagPool

-0.65

ロウィン

-0.65

Portail

-0.65

<pad>

-0.64

<unused21>

-0.64

<unused14>

-0.64

<unused3>

-0.64

POSITIVE LOGITS

 officials

0.33

 police

0.32

 Police

0.30

 authorities

0.27

 Officials

0.27

 olay

0.27

捜査

0.27

 attended

0.26

 said

0.25

 investigation

0.25

Activations Density 0.003%

references to law enforcement and police activity

No Comments

No Known Activations