INDEX

Explanations

terms and phrases 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 @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

She

-0.67

em

-0.63

brechen

-0.63

estin

-0.61

 Mich

-0.59

 aDecoder

-0.58

ag

-0.58

-0.57

-0.56

POSITIVE LOGITS

astify

1.47

 myſelf

1.33

 Notify

1.32

 notifications

1.24

 notify

1.23

 pleaſure

1.22

 Notifications

1.20

 notified

1.20

 purpoſe

1.19

 themſelves

1.18

Activations Density 0.094%

terms and phrases related to notifications and alerts

No Comments

No Known Activations