INDEX

Explanations

references to estates or property

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

########.

-0.77

 AssemblyCulture

-0.69

fromnode

-0.63

matchCondition

-0.60

 Taktlose

-0.59

amentals

-0.56

⅘

-0.55

contentLoaded

-0.55

出版年

-0.55

 disambiguazione

-0.54

POSITIVE LOGITS

 estate

0.49

AddHtmlAttribute

0.47

 vnnd

0.43

 Estate

0.41

 ESTATE

0.40

Items

0.38

OGND

0.38

thebibliography

0.37

 décé

0.36

 doccia

0.35

Activations Density 0.165%

references to estates or property

No Comments

No Known Activations