INDEX

Explanations

programming terminology related to user interface layout and dimensions

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

width, parent, container, size

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

 ContentValues

-0.51

Hentet

-0.50

 Dyck

-0.47

 Picchu

-0.47

waitKey

-0.45

 migrated

-0.45

arraycopy

-0.45

 refugee

-0.45

Belize

-0.45

detective

-0.45

POSITIVE LOGITS

IntoConstraints

0.48

AnchorStyles

0.40

ⓧ

0.40

tagHelperRunner

0.38

innerWidth

0.38

DockStyle

0.37

 thermique

0.36

 kiin

0.35

 intérieure

0.35

 CommonModule

0.35

Activations Density 0.019%

programming terminology related to user interface layout and dimensions

width, parent, container, size

No Comments

No Known Activations