INDEX

Explanations

references to missing individuals or related events

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 Vikipedi

-0.76

Jîn

-0.74

titleMargin

-0.73

withIdentifier

-0.71

borderSide

-0.68

UnitTesting

-0.66

出版年

-0.65

ReusableCell

-0.64

 internetowa

-0.63

SourceChecksum

-0.62

POSITIVE LOGITS

 missing

1.23

 Missing

1.19

Missing

1.12

 disappeared

1.10

 disappearance

1.07

 disappear

1.02

missing

0.99

 MISSING

0.96

 disappearing

0.88

 vanished

0.88

Activations Density 0.272%

references to missing individuals or related events

No Comments

No Known Activations