INDEX

Explanations

references to the "self" keyword, indicating object-oriented programming constructs

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

 Roskov

-0.94

تقاوى

-0.91

StructEnd

-0.69

colage

-0.68

adpleegd

-0.68

RegressionTest

-0.66

SuppressMessage

-0.66

ябре

-0.65

 Rasul

-0.63

 يتيمه

-0.62

POSITIVE LOGITS

Personendaten

0.60

providedIn

0.56

 unknownFields

0.54

Eksteraj

0.51

 OnInit

0.50

tagHelperRunner

0.50

Ссылки

0.48

formik

0.47

半身

0.47

migrationBuilder

0.47

Activations Density 0.001%

references to the "self" keyword, indicating object-oriented programming constructs

No Comments

No Known Activations