INDEX

Explanations

words and phrases associated with wars, battles, or armies

oai_token-act-pair · gemini-2.0-flash

war

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 NSCoder

-0.76

SizeF

-0.67

 Normdatei

-0.62

ConstraintMaker

-0.62

bootstrapcdn

-0.60

krie

-0.58

EndProject

-0.57

woj

-0.54

GOTREF

-0.54

rauch

-0.53

POSITIVE LOGITS

contentLoaded

0.75

RenderAtEndOf

0.62

TestingModule

0.53

onedDateTime

0.53

>--}}

0.52

ⓘ

0.48

zzar

0.48

Semitism

0.47

eavour

0.47

出版年

0.47

Activations Density 18.644%

words and phrases associated with wars, battles, or armies

war

No Comments

No Known Activations