INDEX

Explanations

phrases emphasizing exclusivity or significance

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

"only" followed by another word

np_acts-logits-general · gemini-2.0-flash

following instances of only

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

Viki

-0.65

GeneratedMessage

-0.53

 Verfassung

-0.49

 ejecutivo

-0.49

:✨

-0.49

těte

-0.48

//}

-0.48

</caption>

-0.48

 klara

-0.48

 bakgrund

-0.47

POSITIVE LOGITS

awtextra

0.75

 only

0.67

Only

0.64

 Only

0.62

Демографія

0.62

исленность

0.61

only

0.53

archiviato

0.53

 лишь

0.53

 incomplète

0.52

Activations Density 0.072%

phrases emphasizing exclusivity or significance

"only" followed by another word

following instances of only

No Comments

No Known Activations