INDEX

Explanations

references to statistical terms, particularly related to "mean" and associated concepts

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

"Mean" followed by a subsequent word

np_acts-logits-general · gemini-2.0-flash

mean square

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

ContentAsync

-0.85

awtextra

-0.74

 DialogInterface

-0.74

Aiheesta

-0.69

ViewStyle

-0.68

AntiForgeryToken

-0.66

ChildScrollView

-0.66

prefixer

-0.65

RenderAtEndOf

-0.64

tagHelper

-0.64

POSITIVE LOGITS

tioned

0.81

 litté

0.67

cillor

0.64

urement

0.62

ness

0.62

 Means

0.58

ScreenWidth

0.56

 spirited

0.56

 reversion

0.55

er

0.55

Activations Density 0.078%

references to statistical terms, particularly related to "mean" and associated concepts

"Mean" followed by a subsequent word

mean square

No Comments

No Known Activations