INDEX

Explanations

phrases that indicate presence or visibility in a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 AssemblyTitle

-0.63

ChildScrollView

-0.62

Rüyada

-0.53

DIPSETTING

-0.52

SuspendLayout

-0.51

XmlRootElement

-0.50

 AssemblyProduct

-0.48

__':

-0.48

__":

-0.47

@"/

-0.47

POSITIVE LOGITS

 >=",

0.66

writeFieldEnd

0.64

 Савезне

0.64

Diwedd

0.63

']")

0.58

"}")

0.56

PageContext

0.54

 Guardiola

0.54

SPATH

0.54

 незавершена

0.54

Activations Density 0.338%

phrases that indicate presence or visibility in a context

No Comments

No Known Activations