INDEX

Explanations

occurrences and variations of the word "application."

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

uolo

-0.79

ToArray

-0.74

 تانيه

-0.72

 Huxley

-0.71

用到

-0.69

 thereto

-0.67

 Kraw

-0.67

odacty

-0.66

 Nutella

-0.66

enumi

-0.65

POSITIVE LOGITS

AutoScaleMode

0.73

arResult

0.70

 Roskov

0.68

ppelin

0.63

parsedMessage

0.63

cosystem

0.62

 nahilalakip

0.62

PRNewswire

0.62

BeginContext

0.61

ValueGenerated

0.61

Activations Density 0.016%

occurrences and variations of the word "application."

No Comments

No Known Activations

occurrences and variations of the word "application."

No Comments

No Known Activations