INDEX

Explanations

commented-out sections 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 getView

-0.57

DataAnnotations

-0.56

 seguinte

-0.55

 parvenir

-0.55

 Selatan

-0.53

 vrou

-0.53

Reilly

-0.51

 raggiunto

-0.51

 particolar

-0.51

 affari

-0.50

POSITIVE LOGITS

{//

1.05

);//

1.03

){//

1.00

//

0.99

];//

0.97

}//

0.96

{//

0.96

//

0.95

());//

0.93

"><!--

0.89

Activations Density 0.104%

commented-out sections in code

No Comments

No Known Activations