INDEX

Explanations

JSON object attributes related to user information

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

Preceding a name, id, or other identifier

np_acts-logits-general · gemini-2.0-flash

profile information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

DockStyle

-0.69

 kasarigan

-0.67

 culprits

-0.54

ValueStyle

-0.54

ிறது

-0.52

writers

-0.52

########.

-0.52

 estekak

-0.52

transQ

-0.50

 BeautifulSoup

-0.49

POSITIVE LOGITS

 whom

0.71

 avatar

0.70

 portrait

0.69

 pronouns

0.68

 Profile

0.68

 profile

0.67

 surname

0.67

Biography

0.67

 headshot

0.66

 biography

0.66

Activations Density 0.211%

JSON object attributes related to user information

Preceding a name, id, or other identifier

profile information

No Comments

No Known Activations

JSON object attributes related to user information

Preceding a name, id, or other identifier

profile information

No Comments

No Known Activations