INDEX

Explanations

technical terms and components related to programming frameworks and libraries

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

Code imports or extensions

np_acts-logits-general · gemini-2.0-flash

java/kotlin library prefixes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.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

rawDesc

-0.56

iNdEx

-0.53

TagMode

-0.48

 виправивши

-0.44

layoutControl

-0.42

 sóc

-0.41

 invokingState

-0.40

舺

-0.40

oa̍t

-0.39

stylers

-0.38

POSITIVE LOGITS

VIAF

0.50

 myſelf

0.47

mybatisplus

0.44

Portály

0.44



0.43

ⓧ

0.43

 verſ

0.42

 незавершена

0.42

 Conſ

0.41

MENAFN

0.41

Activations Density 0.249%

technical terms and components related to programming frameworks and libraries

Code imports or extensions

java/kotlin library prefixes

No Comments

No Known Activations