INDEX

Explanations

numeric values associated with health indicators or treatment outcomes

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

jspx

-0.60

AntiForgeryToken

-0.60

 JpaRepository

-0.57

 iprot

-0.55

页面存档备份

-0.54

/$',

-0.54

ListModel

-0.54

zkiem

-0.52

Cuáles

-0.52

Normdaten

-0.51

POSITIVE LOGITS

 الحره

0.75

最快更新

0.71

وردار

0.71

 kaarangay

0.66

].)

0.65

ppure

0.64

 Wiktionnaire

0.63

 sherds

0.63

 blessés

0.61

 AssemblyCompany

0.60

Activations Density 0.007%

numeric values associated with health indicators or treatment outcomes

No Comments

No Known Activations