INDEX

Explanations

terms related to display attributes and properties in programming

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

"display"

np_acts-logits-general · gemini-2.0-flash

display or displaying

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

endforeach

-0.72

 كمان

-0.65

astres

-0.63

 GenerationType

-0.62

슷

-0.58

besar

-0.57

besondere

-0.57

tedt

-0.57

TintMode

-0.57

منبع

-0.57

POSITIVE LOGITS

Displays

0.83

 Displays

0.82

displays

0.78

 displays

0.73

 DISPLAY

0.68

 Display

0.61

 displaying

0.58

 display

0.56

 prominently

0.54

 Denk

0.52

Activations Density 0.144%

terms related to display attributes and properties in programming

"display"

display or displaying

No Comments

No Known Activations