INDEX

Explanations

return statements in code segments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

AndEndTag

-0.57

ConstraintSet

-0.55

 lenker

-0.55

hoeddwyd

-0.54

 față

-0.49

 Cataloging

-0.49

 keben

-0.48

клопе

-0.48

EnumMember

-0.47

 esternos

-0.47

POSITIVE LOGITS

 مرئيه

0.89

return

0.78

 للمعارف

0.71

__":

0.65

 }}"></

0.60

 snippetHide

0.59

 ujednoznacz

0.59

Capítulo

0.59

 return

0.59

はじめに

0.58

Activations Density 0.068%

return statements in code segments

No Comments

No Known Activations