INDEX

Explanations

conditional or optional phrases and potentially new or recent information

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

 Griffin

-0.80

 podjela

-0.73

 Burgess

-0.73

')],

-0.73

)");

-0.73

Datuak

-0.72

 StatefulWidget

-0.72

"]);

-0.72

errorHandler

-0.71

POSITIVE LOGITS

 eſt

0.72

 Thebes

0.72

antaranya

0.71

WebVitals

0.71

 houſe

0.70

 femininos

0.68

 trypto

0.66

 feroit

0.66

 Justine

0.66

 enfans

0.66

Activations Density 0.723%

conditional or optional phrases and potentially new or recent information

No Comments

No Known Activations