INDEX

Explanations

mentions of awards or annual events

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

Follows certain abbreviations or organizations

np_acts-logits-general · gemini-2.0-flash

events and organizations

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

RegressionTest

-0.65

出版年

-0.60

 ویکی‌پدیای

-0.59

sizeCache

-0.59

tslib

-0.55

GeneratedMessage

-0.54

 dintr

-0.54

 venu

-0.54

 dumne

-0.54

脚注の使い方

-0.53

POSITIVE LOGITS

 annual

0.67

“

0.67

+='

0.65

 monthly

0.65

0.64

‘

0.63

Get

0.62

 Future

0.61

 Young

0.58

Activations Density 0.323%

mentions of awards or annual events

Follows certain abbreviations or organizations

events and organizations

No Comments

No Known Activations