INDEX

Explanations

terms and details related to health risks and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

AndEndTag

-0.85

FormTagHelper

-0.76

 سكانية

-0.71

 &___

-0.70

ChildScrollView

-0.70

 cref

-0.64

endphp

-0.63

ViewImports

-0.63

 ujednoznacz

-0.59

ValueStyle

-0.58

POSITIVE LOGITS

ftagPool

0.77

 Roskov

0.76

########.

0.73

 يتيمه

0.57

دانشنامهٔ

0.56

uskas

0.53

 Référence

0.52

 Alderman

0.51

gtest

0.50

 Ressource

0.49

Activations Density 0.049%

terms and details related to health risks and conditions

No Comments

No Known Activations