INDEX

Explanations

elements related to JSON parsing and data manipulation 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 @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 ligiloj

-0.70

 Paglinawan

-0.63

FunctionFlags

-0.62

 estimés

-0.61

NamedQuery

-0.60

 Lightboxes

-0.59

úrese

-0.59

بوابة

-0.57

getColumnIndex

-0.56

InjectAttribute

-0.55

POSITIVE LOGITS

 contents

1.46

 content

1.33

contents

1.21

content

1.19

 text

1.11

Contents

1.08

 Contents

1.07

内容

1.05

 string

1.01

Content

1.01

Activations Density 0.493%

elements related to JSON parsing and data manipulation in code

No Comments

No Known Activations