INDEX

Explanations

high-frequency tokens or symbols that denote structure in text

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

Preceding ordinal numbers

np_acts-logits-general · gemini-2.0-flash

numerical list items or rankings

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 ModelRenderer

-0.84

Ответить

-0.81

Datuak

-0.80

ArrowToggle

-0.78

 TType

-0.70

bootstrapcdn

-0.68

brigens

-0.68

casio

-0.65

 createState

-0.64

 goutte

-0.64

POSITIVE LOGITS

0.75

0.69

vâ

0.57

 russ

0.56

ksanakan

0.55

 مرئيه

0.54

 Ambro

0.54

 Chesterfield

0.53

corrhi

0.53

ContentLoaded

0.53

Activations Density 0.158%

high-frequency tokens or symbols that denote structure in text

Preceding ordinal numbers

numerical list items or rankings

No Comments

No Known Activations