INDEX

Explanations

Java-related classes and methods, particularly those for logging and context management in frameworks

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

Java/C++ code snippets

np_acts-logits-general · gemini-2.0-flash

Javascript framework code and sentences

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

脚注の使い方

-0.78

RegressionTest

-0.74

 mentes

-0.60

تقاوى

-0.59

dhury

-0.54

reportWebVitals

-0.53

glLoad

-0.53

ResumeLayout

-0.53

nsis

-0.52

ondo

-0.52

POSITIVE LOGITS

multer

0.78

InjectAttribute

0.70

 useRouter

0.55

LoggerFactory

0.55

 useParams

0.50

 useDispatch

0.50

 useAppContext

0.50

 NavController

0.50

wapV

0.50

 makeStyles

0.49

Activations Density 0.051%

Java-related classes and methods, particularly those for logging and context management in frameworks

Java/C++ code snippets

Javascript framework code and sentences

No Comments

No Known Activations