INDEX

Explanations

specific terms related to investigation and relationships

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

DoubleQuotes

-0.65

 }}"></

-0.55

 مشين

-0.53

̍

-0.51

}")]

-0.48

 TAMBIÉN

-0.48

 Carls

-0.48

 chi̍t

-0.48

 "'");

-0.48

=?";

-0.47

POSITIVE LOGITS

पया

0.70

IVEREF

0.63

 للاسماء

0.62

GEBURTS

0.61

:✨

0.61

TagMode

0.61

WireFormat

0.59

parsedMessage

0.59

AsUp

0.59

 Réponses

0.57

Activations Density 0.134%

specific terms related to investigation and relationships

No Comments

No Known Activations