INDEX

Explanations

phrases indicating value or worth

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 indígena

-0.46

biendo

-0.46

Providing

-0.45

basicConfig

-0.45

AnchorStyles

-0.44

 Meaning

-0.44

 Providing

-0.44

 TextInputType

-0.42

 meaning

-0.42

Heer

-0.41

POSITIVE LOGITS

 ddelweddau

0.78

ArrowToggle

0.71

 متعلقه

0.68

__':

0.62

AndEndTag

0.62

 незавершена

0.62

ConstraintMaker

0.61

 ligiloj

0.59

enumi

0.58

ideration

0.58

Activations Density 0.240%

phrases indicating value or worth

No Comments

No Known Activations