INDEX

Explanations

connections and relationships between concepts or entities

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

Comes after the word "and"

np_acts-logits-general · gemini-2.0-flash

linking two words

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

Obrázky

-0.52

ModelSerializer

-0.49

iados

-0.48

PathVariable

-0.47

viewDidLoad

-0.47

cioni

-0.47

 mueve

-0.46

reactstrap

-0.46

Бележки

-0.46

principalColumn

-0.46

POSITIVE LOGITS

 Administrativna

0.49

 Italijanski

0.41

 tartalomajánló

0.38

}}}{

0.37

the

0.37

########.

0.35

 disponibilités

0.35

دانشنامهٔ

0.35

 đến

0.35

 ModelExpression

0.35

Activations Density 0.476%

connections and relationships between concepts or entities

Comes after the word "and"

linking two words

No Comments

No Known Activations