INDEX

Explanations

instances of content that initiates or marks the beginning of a new topic or section

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

 kasarigan

-0.78

windowFixed

-0.78

aarrggbb

-0.73

 Lepid

-0.60

richTextPanel

-0.58

 الرياضيه

-0.55

IsMutable

-0.54

 betweenstory

-0.52

łog

-0.51

 Caspar

-0.50

POSITIVE LOGITS

 ComVisible

1.06

 iconFacebook

0.66

vää

0.62

colar

0.62

tagHelperRunner

0.62

CommonModule

0.61

"],

0.59

 contextLoads

0.58

 resourceCulture

0.57

),

0.57

Activations Density 0.042%

instances of content that initiates or marks the beginning of a new topic or section

No Comments

No Known Activations