INDEX

Explanations

repetitive phrases involving the word "have."

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

 been

-0.72

portál

-0.67

 itſelf

-0.65

InjectAttribute

-0.64

SpringBootTest

-0.63

 alſo

-0.60

webElementXpaths

-0.59

 Cæsar

-0.59

 siyang

-0.59

Geplaatst

-0.59

POSITIVE LOGITS

lementation

0.78

UpInside

0.76

دانشنامهٔ

0.75

ImageContext

0.69

Fod

0.67

ulents

0.66

 المعيارى

0.66

boxylic

0.65

krb

0.65

 bVar

0.64

Activations Density 0.026%

repetitive phrases involving the word "have."

No Comments

No Known Activations