INDEX

Explanations

large quantities and measurements related to objects, studies, and groups in various contexts

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sogget

-0.66

 everywhere

-0.65

iotensin

-0.59

انيف

-0.58

ंदीखरीदारी

-0.58

 kaarangay

-0.56

everywhere

-0.56

 Everywhere

-0.56

 itſelf

-0.56

brada

-0.56

POSITIVE LOGITS

 nakalista

0.67

Kaynakça

0.66

AnchorStyles

0.62

 apiece

0.61

分別

0.59

 dozen

0.58

Према

0.55

dozen

0.55

分别是

0.54

//

0.53

Activations Density 0.638%

large quantities and measurements related to objects, studies, and groups in various contexts

No Comments

No Known Activations