INDEX

Explanations

references to product details and related campaign information

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

preceding "page"

np_acts-logits-general · gemini-2.0-flash

website pages

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

 pinulongan

-0.52

 NSCoder

-0.50

ConstraintMaker

-0.49

}))

-0.47

IBar

-0.47

ಉ

-0.46

 resourceCulture

-0.45

 AppBundle

-0.45

prits

-0.44

cristo

-0.44

POSITIVE LOGITS

 page

2.64

page

2.19

 pages

2.16

 Page

2.02

Page

1.97

 pagina

1.84

 PAGE

1.84

pages

1.77

 página

1.75

 페이지

1.70

Activations Density 0.305%

references to product details and related campaign information

preceding "page"

website pages

No Comments

No Known Activations