INDEX

Explanations

references to individuals and organizations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

 OnInit

-0.40

 didReceive

-0.37

 reaſon

-0.32

 poffible

-0.30

 chance

-0.29

ByPrimaryKey

-0.29

 whole

-0.29

As

-0.29

baomidou

-0.29

dur

-0.28

POSITIVE LOGITS

 Numerade

0.85

ंदीखरीदारी

0.82

 propOrder

0.81

EndGlobalSection

0.80

contentLoaded

0.79

 Normdatei

0.77

 мәкал

0.75

Aholisi

0.75

 Мексичка

0.75

complexContent

0.73

Activations Density 3.075%

references to individuals and organizations in various contexts

No Comments

No Known Activations