INDEX

Explanations

references to scientific journals and their respective articles

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

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

 anhydride

-0.49

localtime

-0.49

 parach

-0.48

 gubern

-0.48

ivotopis

-0.48

XmlAccessorType

-0.47

 informée

-0.47

melons

-0.47

HasKey

-0.46

 zove

-0.46

POSITIVE LOGITS

########.

0.69

FormTagHelper

0.60

LookAnd

0.59

PerformLayout

0.59

webElementXpaths

0.57

:✨

0.56

EndInit

0.55

 оригіналу

0.54

makeConstraints

0.54

MemoryWarning

0.54

Activations Density 0.100%

references to scientific journals and their respective articles

No Comments

No Known Activations