INDEX

Explanations

references to "processor" within technical contexts

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

preprocessor directives

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

rzez

-0.37

 debout

-0.35

 helado

-0.32

routeProvider

-0.32

 espelho

-0.31

 aparelho

-0.31

 colère

-0.31

 vostra

-0.31

stateProvider

-0.29

WaitGroup

-0.29

POSITIVE LOGITS

 TextAppearance

0.65

MultipartFile

0.60

PasswordEncoder

0.59

 ſind

0.54

 scanning

0.54

 protoimpl

0.54

InjectAttribute

0.53

tawan

0.53

canes

0.53

leeve

0.52

Activations Density 0.000%

references to "processor" within technical contexts

preprocessor directives

No Comments

No Known Activations