INDEX

Explanations

terms and phrases related to display systems or visuals

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

"display" and its variations

np_acts-logits-general · gemini-2.0-flash

display panels, display mode

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

슷

-0.83

 rêver

-0.78

@"/

-0.72

ürzt

-0.71

 volontaire

-0.69

 foncé

-0.69

besar

-0.68

__":

-0.67

 fallu

-0.67

 كمان

-0.67

POSITIVE LOGITS

 displays

1.46

 Displays

1.44

 display

1.42

 DISPLAY

1.40

Displays

1.40

displays

1.35

 Display

1.33

display

1.19

 displaying

1.19

Display

1.18

Activations Density 0.092%

terms and phrases related to display systems or visuals

"display" and its variations

display panels, display mode

No Comments

No Known Activations