INDEX

Explanations

references to regulatory agencies and approvals related to health and safety

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

Governmental organizations or agencies

np_acts-logits-general · gemini-2.0-flash

government agency names

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

 <=",

-0.48

AutoresizingMask

-0.46

 surla

-0.45

RegressionTest

-0.40

Personensuche

-0.38

 ujednoznacz

-0.38

FontOfSize

-0.37

wapV

-0.36

 kasarigan

-0.36

vertra

-0.35

POSITIVE LOGITS

 NASA

0.94

NASA

0.86

FDA

0.85

FBI

0.76

FDA

0.75

EPA

0.71

 USDA

0.69

FAA

0.69

 OSHA

0.68

CDC

0.66

Activations Density 0.365%

references to regulatory agencies and approvals related to health and safety

Governmental organizations or agencies

government agency names

No Comments

No Known Activations