INDEX

Explanations

mathematical expressions and programming-related syntax

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

math notation and surrounding 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

 surla

-0.77

 ligiloj

-0.71

出版年

-0.69

expandindo

-0.63

 виправивши

-0.57

Hozzáférés

-0.53

 saites

-0.52

VersionUID

-0.52

 HasFactory

-0.50

 Biôgrafia

-0.49

POSITIVE LOGITS

endregion

0.33

 wireType

0.33

transQ

0.33

 çekilen

0.32

 artificial

0.31

Artificial

0.30

 RIPRODUZIONE

0.30

 kuns

0.29

 znal

0.28

 thậm

0.28

Activations Density 0.147%

mathematical expressions and programming-related syntax

math notation and surrounding words

No Comments

No Known Activations