INDEX

Explanations

references to specific products and brands, particularly those beginning with 'Z'

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

starting with "Z" or "Ze"

np_acts-logits-general · gemini-2.0-flash

ze (followed by phyr, in, bras, itschrift, us)

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

}*/

-0.60

globalData

-0.57

>*/

-0.55

Rohy

-0.54

 esternos

-0.53

twimg

-0.53

TagHelper

-0.52

})*/

-0.52

});*/

-0.52

тьяна

-0.52

POSITIVE LOGITS

zag

0.66

 BoxFit

0.62

saraba

0.59

ZX

0.55

ZE

0.55

ZZZ

0.55

Zin

0.54

ZR

0.54

0.53

Zat

0.53

Activations Density 0.215%

references to specific products and brands, particularly those beginning with 'Z'

starting with "Z" or "Ze"

ze (followed by phyr, in, bras, itschrift, us)

No Comments

No Known Activations