INDEX

Explanations

opening brackets or array indicators in coding structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 iſt

-0.77

MigrationBuilder

-0.71

 ―――――

-0.71

AndEndTag

-0.70

Datuak

-0.70

buttonBar

-0.70

'</

-0.67

 AssemblyCompany

-0.67

 Taktlose

-0.67

 resourceCulture

-0.67

POSITIVE LOGITS

([

0.99

={[

0.87

原始内容存档于

0.85

}=[

0.84

：[

0.81

{[

0.77

=[

0.76

([[

0.74

+[

0.72

<[

0.72

Activations Density 0.211%

opening brackets or array indicators in coding structures

No Comments

No Known Activations