INDEX

Explanations

sections of code or document formatting elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 arşivlendi

-0.64

reszcie

-0.60

SPATH

-0.57

iformis

-0.56

 Offisielt

-0.55

 perfetta

-0.54

NullException

-0.54

?''

-0.54

 complémentaires

-0.54

 useContext

-0.54

POSITIVE LOGITS

 Италијани

0.92

 EconPapers

0.76

MigrationBuilder

0.71

 Exacts

0.67

 estekak

0.64

migrationBuilder

0.63

 propOrder

0.63

 насељу

0.63

 mxArray

0.62

 CanadaChoose

0.60

Activations Density 0.000%

sections of code or document formatting elements

No Comments

No Known Activations