INDEX

Explanations

attributes and metadata related to items in a structured format, such as IDs, names, and types

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

帖最后由

-0.73

انيف

-0.67

 архивлан

-0.66

abestanden

-0.61

Попис

-0.61

LElement

-0.60

 ویکی‌پدیا

-0.60

 оригіналу

-0.59

endphp

-0.59

RegistryLite

-0.59

POSITIVE LOGITS

 Neale

0.58

########.

0.58

ớm

0.57

fuo

0.57

 simplifying

0.56

//

0.56

 Reſ

0.56

phazard

0.54

괄

0.54

 garaje

0.54

Activations Density 0.034%

attributes and metadata related to items in a structured format, such as IDs, names, and types

No Comments

No Known Activations