INDEX

Explanations

references to diabetes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 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

 vettoriale

-0.67

astéroïdes

-0.66

upuesto

-0.63

 giudi

-0.60

 timmar

-0.59

 AssemblyCulture

-0.59

 geolog

-0.59

 Garnet

-0.59

 Juifs

-0.58

 cuticle

-0.58

POSITIVE LOGITS

endregion

1.25

 diabetes

1.19

 Diabetes

1.02

endif

1.01

diabetes

0.88

Diabetes

0.88

 endregion

0.87

 diabetics

0.86

dia

0.84

 diabetic

0.83

Activations Density 0.054%

references to diabetes in various contexts

No Comments

No Known Activations