INDEX

Explanations

references to completion or conclusion

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

ever

-0.64

 AttributeSet

-0.62

spyOn

-0.59

צע

-0.58

UObject

-0.57

OGND

-0.57

gena

-0.56

omenta

-0.52

argli

-0.51

 ModelExpression

-0.51

POSITIVE LOGITS

EndTag

0.61

enumii

0.57

 Danach

0.54

PostExecute

0.54

ilogue

0.54

结束后

0.52

mappedBy

0.51

ậy

0.50

 klaar

0.50

 Graduation

0.49

Activations Density 0.419%

references to completion or conclusion

No Comments

No Known Activations