INDEX

Explanations

expressions related to object properties and calculations involving dimensions

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

chyma

-0.54

 fallu

-0.51

 endian

-0.51

ValueStyle

-0.49

 AssemblyCulture

-0.49

appliquer

-0.49

 Continent

-0.48

 tachycardia

-0.48

 inaug

-0.48

hassee

-0.47

POSITIVE LOGITS

ⓧ

0.60

mybatisplus

0.59

 елның

0.56

WireFormatLite

0.56

zanas

0.54

ShowDialog

0.54

"=>$

0.52

écu

0.52

 unknownFields

0.52

")==

0.52

Activations Density 0.629%

expressions related to object properties and calculations involving dimensions

No Comments

No Known Activations