INDEX

Explanations

specific spatial relationships and locations within a described environment

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

"of" preceding another word

np_acts-logits-general · gemini-2.0-flash

of the following noun phrases

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

цездатний

-0.78

 يتيمه

-0.77

>--}}

-0.73

}{*}{}

-0.71

Tikang

-0.68

 Theſe

-0.66

DrawerToggle

-0.66

〢

-0.65

 ་་

-0.64

Efq

-0.63

POSITIVE LOGITS

of

0.50

λίου

0.48

 każdego

0.48

bladet

0.46

رش

0.46

 each

0.46

 varje

0.43

 Gründer

0.43

OfMonth

0.42

 grated

0.42

Activations Density 0.302%

specific spatial relationships and locations within a described environment

"of" preceding another word

of the following noun phrases

No Comments

No Known Activations