INDEX

Explanations

references to political events and entities

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

foreign names and words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 مشين

-0.59

 Италијани

-0.56

 estekak

-0.52

 Italijani

-0.50

Véxase

-0.43

WithIOException

-0.43

 ivelany

-0.42

 onBind

-0.41

expandindo

-0.40

########.

-0.38

POSITIVE LOGITS

yntaxException

0.48

 AssemblyTitle

0.47

存于互联网档案馆

0.46

 يتيمه

0.44

UnusedPrivate

0.43

 rallado

0.42

 morire

0.41

 pioggia

0.40

complexContent

0.40

 scurt

0.40

Activations Density 0.042%

references to political events and entities

foreign names and words

No Comments

No Known Activations