INDEX

Explanations

terms related to disease and illness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 AssemblyCulture

-0.75

Mermaid

-0.71

 ciascuno

-0.70

 Schwangerschaft

-0.68

 arşivlendi

-0.67

 GONNA

-0.67

 Guel

-0.67

 auroit

-0.67

Zet

-0.67

thodon

-0.67

POSITIVE LOGITS

 disease

2.06

 diseases

1.92

 Disease

1.82

 Diseases

1.70

 DISEASE

1.68

Disease

1.63

disease

1.58

 DISEASES

1.58

Diseases

1.58

diseases

1.38

Activations Density 0.096%

terms related to disease and illness

No Comments

No Known Activations