INDEX

Explanations

terms related to data types in programming, specifically unsigned integers

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

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

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

olol

-0.71

autorité

-0.69

lapia

-0.68

DeleteMapping

-0.68

 buhay

-0.67

 AspNetCore

-0.65

ilitar

-0.65

endphp

-0.65

dhury

-0.65

HasAnnotation

-0.65

POSITIVE LOGITS

unsigned

1.19

Unsigned

0.98

 unsigned

0.97

 تضيفلها

0.84

Altern

0.77

 Ches

0.72

hove

0.70

ars

0.69

UNSIGNED

0.69

Pus

0.68

Activations Density 0.003%

terms related to data types in programming, specifically unsigned integers

No Comments

No Known Activations