INDEX

Explanations

patterns or structures within formal documents or texts

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

Non-English Wikipedia metadata and identifiers

np_acts-logits-general · gemini-2.0-flash

and followed by in

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

Viited

-0.83

UnusedPrivate

-0.78

 Administrativna

-0.76

 Италијани

-0.74

 kasarigan

-0.70

 defaultstate

-0.68

WarningLevel

-0.63

 myſelf

-0.63

Lähteet

-0.62

 Italijanski

-0.61

POSITIVE LOGITS

SourceChecksum

0.53

 مُعرِّف

0.53

بوابة

0.51

czeniu

0.47

acka

0.47

impri

0.46

 CONCLUSION

0.46

 contacter

0.45

HasAnnotation

0.45

دانشنامهٔ

0.43

Activations Density 0.102%

patterns or structures within formal documents or texts

Non-English Wikipedia metadata and identifiers

and followed by in

No Comments

No Known Activations