INDEX

Explanations

details related to product specifications, particularly regarding sizes and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Politiker

-0.50

Carreira

-0.50

écnicas

-0.49

bootstrapcdn

-0.48

ppb

-0.46

 मिन

-0.44

valdi

-0.44

">//

-0.42

 scape

-0.42

TRIBUN

-0.42

POSITIVE LOGITS

 size

1.50

 sizes

1.40

 sizing

1.32

 Size

1.28

size

1.26

 Sizes

1.22

Size

1.19

 SIZE

1.18

 Sizing

1.09

sizes

1.06

Activations Density 0.114%

details related to product specifications, particularly regarding sizes and measurements

No Comments

No Known Activations