INDEX

Explanations

terms related to military action and conflict

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

KommentareTeilen

-0.44

Victorian

-0.43

 Vallarta

-0.42

 Fontana

-0.42

 Serif

-0.42

 frå

-0.41

Amsterdam

-0.41

 Tulip

-0.41

 zufolge

-0.41

 Victorian

-0.40

POSITIVE LOGITS

 troops

0.81

 army

0.73

 commander

0.73

 armies

0.66

commander

0.65

 battalion

0.65

 reinforcements

0.65

 enemy

0.65

 combat

0.64

 Krieg

0.63

Activations Density 0.843%

terms related to military action and conflict

No Comments

No Known Activations