INDEX

Explanations

XML schema definitions and associated elements in code

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

XML schema instance

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

transQ

-0.69

 JpaRepository

-0.63

 PeEnEo

-0.54

erialize

-0.54

ituary

-0.52

Tikang

-0.52

 للاسماء

-0.51

⋙

-0.50

Obituary

-0.50

urlpatterns

-0.50

POSITIVE LOGITS

xsi

1.48

XmlType

0.49

Diwedd

0.39

complexContent

0.39

 ISNI

0.38

chtenstein

0.38

 defaultstate

0.38

elemField

0.37

xsd

0.36

XSSF

0.36

Activations Density 0.005%

XML schema definitions and associated elements in code

XML schema instance

No Comments

No Known Activations