INDEX

Explanations

specific reference identifiers or codes that indicate categorization or classification in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

">//

-0.57

 році

-0.56

 StatelessWidget

-0.54

 externi

-0.53

iermark

-0.51

 GoogleFonts

-0.51

Obrázky

-0.50

ButtonStyle

-0.50

KindOfClass

-0.50

енча

-0.49

POSITIVE LOGITS

inn

0.70

 ExecuteAsync

0.68

 heapq

0.66

 незавершена

0.64

الإنجليزية

0.63

NCT

0.63

/>";

0.63

nsec

0.63

//

0.62

 }^{[

0.60

Activations Density 1.962%

specific reference identifiers or codes that indicate categorization or classification in various contexts

No Comments

No Known Activations