INDEX

Explanations

mathematical notations and symbols related to linear algebra and tensor products

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DoubleQuotes

-0.69

 Organized

-0.66

 समीक्षाओं

-0.66

 CONV

-0.64

icksburg

-0.62

 متعلقه

-0.62

StrictEqual

-0.62

脚注の使い方

-0.61

})*/

-0.60

tekend

-0.59

POSITIVE LOGITS

SceneManagement

0.57

getItemId

0.51

getFullYear

0.47

κτηρισ

0.45

GetAxis

0.45

AsUp

0.44

 resourceCulture

0.44

 declarat

0.43

 argc

0.40

Integer

0.40

Activations Density 1.164%

mathematical notations and symbols related to linear algebra and tensor products

No Comments

No Known Activations