INDEX

Explanations

phrases related to measurement or quantification

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

Numbers and percentages

np_acts-logits-general · gemini-2.0-flash

final minutes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

atifying

-0.57

 tartalomajánló

-0.51

 junit

-0.49

 earlier

-0.47

})();

-0.46

 iArr

-0.46

setViewportView

-0.45

tibus

-0.45

iect

-0.44

xture

-0.44

POSITIVE LOGITS

VersionUID

0.75

WireFormatLite

0.59

enterOuterAlt

0.59

elemField

0.59

 елның

0.57

FunctionFlags

0.57

 uVar

0.57

 mergeFrom

0.56

 appunto

0.56

lav

0.56

Activations Density 1.095%

phrases related to measurement or quantification

Numbers and percentages

final minutes

No Comments

No Known Activations