INDEX

Explanations

references to historical events and dates

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

 يتيمه

-0.61

ⓘ

-0.58

 ostavi

-0.57

 ModelExpression

-0.55

GeneratedValue

-0.52

 Deserialize

-0.51

alanta

-0.48

homonymie

-0.48

 unknownFields

-0.48

DATABASES

-0.47

POSITIVE LOGITS

 فريبيس

0.65

LookAnd

0.64

Бележки

0.53

koala

0.52

DispatchToProps

0.50

BeginInit

0.50

 Obtenez

0.49

 урна

0.49

Edd

0.48

 kaynağından

0.47

Activations Density 0.447%

references to historical events and dates

No Comments

No Known Activations