INDEX

Explanations

programming constructs and concepts related to class and view management in software development

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

view in code

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

 pró

-0.45

eleste

-0.42

족

-0.37

 tips

-0.36

 meaningful

-0.36

 family

-0.35

ersk

-0.35

FXMLLoader

-0.35

 acid

-0.34

 salt

-0.33

POSITIVE LOGITS

 Italijanski

0.70

prefixer

0.63

0.59

BASEPATH

0.58

mvp

0.57

 informée

0.57

Personensuche

0.55

 ویکی‌پدی

0.52

 kasarigan

0.52

endpush

0.52

Activations Density 0.002%

programming constructs and concepts related to class and view management in software development

view in code

No Comments

No Known Activations