INDEX

Explanations

phrases related to studies and research findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 noqa

-0.54

faz

-0.53

Imp

-0.51

Imp

-0.51

imp

-0.50

 disponibilités

-0.50

 vole

-0.49

 interag

-0.49

暇

-0.48

う

-0.48

POSITIVE LOGITS

tagHelperRunner

0.98

InjectAttribute

0.79

titleMargin

0.73

ScopeManager

0.68

IntoConstraints

0.67

الحياه

0.67

webElementGuid

0.66

setVerticalGroup

0.65

 tartalomajánló

0.65

ViewFeatures

0.63

Activations Density 0.553%

phrases related to studies and research findings

No Comments

No Known Activations