INDEX

Explanations

programming or markup language terminology related to structure and formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

ViewFeatures

-1.04

rrggbb

-0.75

mybatisplus

-0.74

المناصب

-0.70

 imageNamed

-0.60

 GenerationType

-0.60

 للمعارف

-0.59

initializeApp

-0.59

الحياه

-0.58

@(

-0.57

POSITIVE LOGITS

complexContent

1.49

ERVIS

1.13

 uska

0.77

NKC

0.69

 useParams

0.58

Lähteet

0.56

 trattano

0.51

KURZBESCHREIBUNG

0.51

phosa

0.50

 sposob

0.49

Activations Density 0.001%

programming or markup language terminology related to structure and formatting

No Comments

No Known Activations