INDEX

Explanations

patterns involving numerical values or ratings

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

endphp

-0.60

IContainer

-0.54

guisement

-0.52

 straws

-0.50

 histogram

-0.48

Locality

-0.48

 estimés

-0.48

 sociologist

-0.47

 complainant

-0.46

的一个

-0.45

POSITIVE LOGITS

contentLoaded

0.83

Geplaatst

0.81

findpost

0.80

tagHelperRunner

0.75

Jereo

0.75

 invokingState

0.75

StructEnd

0.70

下载附件

0.68

AccessorTable

0.66

ברס

0.65

Activations Density 0.007%

patterns involving numerical values or ratings

No Comments

No Known Activations