INDEX

Explanations

statements that indicate the existence or presence of something

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

"There" followed by state-of-being verbs

np_acts-logits-general · gemini-2.0-flash

there is / are / were

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

ibatis

-0.62

Lähteet

-0.60

setViewportView

-0.54

fastjson

-0.53

reactstrap

-0.51

enumi

-0.49

ioutil

-0.49

猴

-0.49

 SUCH

-0.48

StreetMap

-0.48

POSITIVE LOGITS

oredCriteria

0.72

rrggbb

0.63

})));

0.60

}),

0.58

 arvio

0.57

 remains

0.55

Datuak

0.55

parsedMessage

0.54

 remain

0.54

 utafitiHapana

0.54

Activations Density 0.177%

statements that indicate the existence or presence of something

"There" followed by state-of-being verbs

there is / are / were

No Comments

No Known Activations