INDEX

Explanations

different types of object or attribute-related information in the content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 bezeichneter

-0.61

Controllo

-0.57

 autorytatywna

-0.57

Portály

-0.49

存于互联网档案馆

-0.46

enterian

-0.44



-0.43

 Undang

-0.43

 contactez

-0.42

خوش

-0.42

POSITIVE LOGITS

terdam

0.73

 MainAxisSize

0.72

skjaer

0.72

0.71

 المعيارى

0.70

MessageTagHelper

0.69

 jButton

0.68

//

0.67

 vPvB

0.66

pyx

0.65

Activations Density 0.048%

different types of object or attribute-related information in the content

No Comments

No Known Activations

different types of object or attribute-related information in the content

No Comments

No Known Activations