INDEX

Explanations

terms indicating unusual or atypical medical conditions or presentations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

LookAnd

-0.77

 AssemblyVersion

-0.76

XmlRootElement

-0.73

 companyId

-0.69

 GenerationType

-0.67

 crossorigin

-0.65

flüs

-0.65

σκε

-0.65

\}\\

-0.64

 Winkler

-0.64

POSITIVE LOGITS

 unusual

1.50

 uncommon

1.41

unusual

1.34

 abnormal

1.33

 Unusual

1.28

Unusual

1.22

 normal

1.19

 usual

1.16

usual

1.13

 unusually

1.10

Activations Density 0.140%

terms indicating unusual or atypical medical conditions or presentations

No Comments

No Known Activations