INDEX

Explanations

terms related to automated service or machinery

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

Follows a capitalized word

np_acts-logits-general · gemini-2.0-flash

unique words in quotes or lists

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

ChildScrollView

-0.94

 defaultstate

-0.94

'{@

-0.85

ImageContext

-0.84

 مشين

-0.82

GraphicsUnit

-0.82

 MainAxisSize

-0.80

ंदीखरीदारी

-0.79

存于互联网档案馆

-0.78

setVerticalGroup

-0.78

POSITIVE LOGITS

0.54

 arrival

0.54

 adult

0.53

 adopts

0.52

DIY

0.51

 kids

0.49

dfunding

0.47

Men

0.47

 Arrival

0.47

 women

0.47

Activations Density 0.078%

terms related to automated service or machinery

Follows a capitalized word

unique words in quotes or lists

No Comments

No Known Activations