INDEX

Explanations

testing functions and events 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 @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 مشين

-0.81

 Walkover

-0.56

✭✭

-0.56

sieurs

-0.55

ChildScrollView

-0.51

 الرياضيه

-0.50

 step

-0.50

IMON

-0.49

babel

-0.49

multirow

-0.48

POSITIVE LOGITS

describe

1.39

Describe

0.92

 Describe

0.75

Witam

0.73

Click

0.67

 Xunit

0.65

 itſelf

0.64

MetaObject

0.62

Discuss

0.62

Referències

0.61

Activations Density 0.078%

testing functions and events in code

No Comments

No Known Activations