INDEX

Explanations

references to content-related topics and data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ఔ

-0.66

JspWriter

-0.57

 IBOutlet

-0.56

HAV

-0.55

WindowConstants

-0.55

 Thayer

-0.53

 phút

-0.51

☛

-0.51

 Umum

-0.51

ikes

-0.51

POSITIVE LOGITS

 contents

0.81

 getContent

0.75

 material

0.70

 setContent

0.69

 Content

0.69

 content

0.66

stoffe

0.63

 multitudes

0.63

 Contents

0.62

 metter

0.61

Activations Density 0.070%

references to content-related topics and data analysis

No Comments

No Known Activations