INDEX

Explanations

the beginning of sections in a document, particularly marked by structural indicators

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tvguidetime

-0.66

 useNavigate

-0.60

 المعيارى

-0.59

 pinulongan

-0.58

ValueGeneration

-0.56

 PopupWindow

-0.56

 estekak

-0.56

 useDispatch

-0.55

Kelebihan

-0.54

Organisateur

-0.54

POSITIVE LOGITS

ⓧ

0.69

:✨

0.61

rxjs

0.56

RuleContext

0.52

WriteAttribute

0.51

 Gregorian

0.51

Географи

0.49

addGroup

0.48

nius

0.48

addGap

0.48

Activations Density 0.044%

the beginning of sections in a document, particularly marked by structural indicators

No Comments

No Known Activations