INDEX

Explanations

structural elements of programming code

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

expo or programming context

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

ESOME

-0.47

élément

-0.41

 bezit

-0.40

 Edelman

-0.39

 Вікіпе

-0.39

 öner

-0.38

bold

-0.37

拥

-0.36

 verfügt

-0.35

เหลือ

-0.35

POSITIVE LOGITS

 ModelExpression

0.78

ReusableCell

0.70

########.

0.63

 defaultstate

0.57

 kasarigan

0.57

!*\

0.55

 useEffect

0.52

Abitanti

0.52

RenderAtEndOf

0.52

GEBURTSDATUM

0.51

Activations Density 0.002%

structural elements of programming code

expo or programming context

No Comments

No Known Activations