INDEX

Explanations

medical terms and references to specific diseases and treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Ellis

-0.76

 Hooper

-0.73

 Mathis

-0.70

posta

-0.68

 Moreira

-0.66

pho

-0.65

 Winkler

-0.64

Pho

-0.63

 Ottawa

-0.63

Ellis

-0.62

POSITIVE LOGITS

Zeneca

1.07

Tembelea

0.97

(!__

0.93

Kuj

0.92

DeleteBehavior

0.92

 AssemblyVersion

0.92

 Cavendish

0.91

 getIntent

0.90

 Esco

0.89

Tey

0.88

Activations Density 1.392%

medical terms and references to specific diseases and treatments

No Comments

No Known Activations