INDEX

Explanations

locations and references related to laboratories and studios

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

preceding "laboratory," "studio," or "factory."

np_acts-logits-general · gemini-2.0-flash

places like laboratory, studio, clinic, factory

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

 présidentielle

-0.46

 Persson

-0.44

})));

-0.43

 grze

-0.43

phosa

-0.42

eraard

-0.40

 Drapeau

-0.40

 Nederlandse

-0.40

 umana

-0.40

prechung

-0.40

POSITIVE LOGITS

الحياه

0.52

 Wikimedijinoj

0.51

LookAnd

0.49

 Hosp

0.48

 BoxFit

0.47

 LoggerFactory

0.47

principalColumn

0.47

 Floor

0.47

 дописавши

0.47

 Playhouse

0.47

Activations Density 0.535%

locations and references related to laboratories and studios

preceding "laboratory," "studio," or "factory."

places like laboratory, studio, clinic, factory

No Comments

No Known Activations