INDEX

Explanations

terms related to notifications and alerts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 radium

-0.70

Референце

-0.69

ंदीखरीदारी

-0.68

UIControlState

-0.65

 Rigidbody

-0.65

Биография

-0.64

FieldBuilder

-0.64

DeleteBehavior

-0.63

 Wreck

-0.62

DebuggerNonUser

-0.61

POSITIVE LOGITS

 notification

2.42

 notifications

2.30

 Notification

2.21

Notification

2.19

 Notifications

2.19

notification

2.06

Notifications

2.00

 notify

1.99

 notified

1.89

 Notify

1.88

Activations Density 0.065%

terms related to notifications and alerts

No Comments

No Known Activations