INDEX

Explanations

references to government and legal entities

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

"U.S." or abbreviation of "United States"

np_acts-logits-general · gemini-2.0-flash

U.S. abbreviations

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

 Италијани

-0.59

ChildScrollView

-0.59

ఔ

-0.56

BufferException

-0.54

ufficient

-0.52

routeProvider

-0.51

MessageTagHelper

-0.51

makeText

-0.50

RegressionTest

-0.49

parsedMessage

-0.48

POSITIVE LOGITS

 Serikat

0.61

US

0.58

US

0.53

Us

0.52

 الأمريكية

0.51

 Federal

0.46

🇺🇸

0.46

amerikan

0.45

USC

0.45

Us

0.44

Activations Density 0.216%

references to government and legal entities

"U.S." or abbreviation of "United States"

U.S. abbreviations

No Comments

No Known Activations