INDEX

Explanations

quantitative information relevant to health, particularly concerning common diseases and mortality rates

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

Preceding superlatives (biggest, most, largest)

np_acts-logits-general · gemini-2.0-flash

leading, largest, second, biggest

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 propOrder

-0.86

 AssemblyCulture

-0.63

KommentareTeilen

-0.62

XmlAccessType

-0.59

GOTREF

-0.59

buzo

-0.57

AccessorTable

-0.55

verwijspagina

-0.55

ValueStyle

-0.55

MessageOf

-0.54

POSITIVE LOGITS

 largest

1.61

 major

1.43

largest

1.36

 Largest

1.28

 biggest

1.24

major

1.24

Largest

1.14

biggest

1.11

 significant

1.05

Major

1.03

Activations Density 0.230%

quantitative information relevant to health, particularly concerning common diseases and mortality rates

Preceding superlatives (biggest, most, largest)

leading, largest, second, biggest

No Comments

No Known Activations