INDEX

Explanations

phrases indicating location or position in relation to other elements

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

 ujednoznacz

-0.74

gyű

-0.57

 manna

-0.57

 brancas

-0.57

 kasarigan

-0.57

 cascada

-0.57

 Lingkungan

-0.56

ValueStyle

-0.56

 mijne

-0.55

 vrijwilli

-0.55

POSITIVE LOGITS

انگلیسی

0.71

Nev

0.71

 Biel

0.67

ән

0.67

日在

0.66

 Bres

0.64

قایناق‌لار

0.63

 chó

0.62

OrBuilder

0.62

anin

0.62

Activations Density 0.035%

phrases indicating location or position in relation to other elements

No Comments

No Known Activations