INDEX

Explanations

numerical representations and mathematical notation

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

setupUi

-0.75

DeleteBehavior

-0.73

GEBURTSDATUM

-0.72

makeConstraints

-0.72

 ExecuteAsync

-0.69

writeFieldEnd

-0.69

IANGLES

-0.68

 informée

-0.68

usda

-0.68

UnsafeEnabled

-0.66

POSITIVE LOGITS

 culture

0.60

 CULTURE

0.59

 commonest

0.56

 Syner

0.52

 Culture

0.52

culture

0.52

 Panels

0.51

 Cult

0.51

 cultura

0.50

 plantain

0.50

Activations Density 0.456%

numerical representations and mathematical notation

No Comments

No Known Activations