INDEX

Explanations

variations of the prefix "wi" and related terms

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

"Wi" followed by other characters

np_acts-logits-general · gemini-2.0-flash

words starting with 'wi'

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

classnames

-0.62

 bayer

-0.57

sterdam

-0.56

merkungen

-0.55

cshtml

-0.55

htdocs

-0.53

={[

-0.52

LANDS

-0.51

mäßigen

-0.50

 Bayer

-0.50

POSITIVE LOGITS

Wis

0.80

uxxxx

0.72

Wis

0.72

Wib

0.72

wi

0.70

 Wiss

0.68

writeFieldEnd

0.67

Viz

0.66

Wiz

0.65

WIT

0.65

Activations Density 0.154%

variations of the prefix "wi" and related terms

"Wi" followed by other characters

words starting with 'wi'

No Comments

No Known Activations