INDEX

Explanations

terminology and data points related to scientific measurements or conditions

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

पया

-0.66

InjectMocks

-0.56

 ujednoznacz

-0.56

 SEDS

-0.54

hassee

-0.54

 الحره

-0.54

 étrangères

-0.54

UpInside

-0.53

BeginInit

-0.52

ngdoc

-0.51

POSITIVE LOGITS

IsContent

0.63

__*/

0.60

]")]

0.57

ikä

0.55

ক্ত

0.53

ResumeLayout

0.53

ölker

0.52

ValueStyle

0.51

RetentionPolicy

0.49

ApiModelProperty

0.49

Activations Density 0.660%

terminology and data points related to scientific measurements or conditions

No Comments

No Known Activations