INDEX

Explanations

phrases indicating beginnings or endings of events

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

"end" or "beginning" followed by "of"

np_acts-logits-general · gemini-2.0-flash

beginning and end

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Efq

-0.69

SourceChecksum

-0.69

lhes

-0.59

findpost

-0.58

ziosi

-0.57

Geograf

-0.54

addCriterion

-0.54

jsxFileName

-0.53

".$_

-0.53

omenclature

-0.53

POSITIVE LOGITS

تقاوى

0.70

end

0.63

끝

0.56

Rohy

0.54

aarrggbb

0.52

eward

0.52

InstanceState

0.51

Portail

0.50

Kras

0.48

DockStyle

0.48

Activations Density 0.158%

phrases indicating beginnings or endings of events

"end" or "beginning" followed by "of"

beginning and end

No Comments

No Known Activations