INDEX

Explanations

function and class names typically used in programming, especially related to mathematical operations and HTTP requests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 referenties

-0.73

äfts

-0.61

 समीक्षाओं

-0.58

########.

-0.57

findpost

-0.57

endphp

-0.56

 faune

-0.55

 AssemblyCompany

-0.54

 Entdecke

-0.53

 numberOfRows

-0.53

POSITIVE LOGITS

GEBURTSDATUM

0.95

Personendaten

0.68

twimg

0.65

Hentet

0.63

XmlAccessorType

0.61

assis

0.58

Einzelnachweise

0.58

لينكات

0.55

 oprot

0.55

 ujednoznacz

0.52

Activations Density 0.042%

function and class names typically used in programming, especially related to mathematical operations and HTTP requests

No Comments

No Known Activations