INDEX

Explanations

programming constructs and keywords related to variable definitions and structure in code

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

QMetaType

-0.68

脚注の使い方

-0.62

xsi

-0.56

Datuak

-0.54

codegen

-0.46

 ***!

-0.46

ografija

-0.45

FieldNumber

-0.45

Geografie

-0.45

inalis

-0.44

POSITIVE LOGITS

 FontWeight

1.49

 MonoBehaviour

1.41

XmlAccessorType

0.98

HtmlAttribute

0.95

 jPanel

0.93

styleUrls

0.85

glVertex

0.83

 jLabel

0.82

AddTagHelper

0.80

 مشين

0.80

Activations Density 0.011%

programming constructs and keywords related to variable definitions and structure in code

No Comments

No Known Activations