INDEX

Explanations

terms related to patient care interventions and characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Riley

-0.89

σ

-0.85

 Varela

-0.82

σ

-0.78

 Williams

-0.77

Riley

-0.76

Ali

-0.74

sigma

-0.70

 WILLIAMS

-0.67

Liu

-0.67

POSITIVE LOGITS

 Lorraine

0.90

AndEndTag

0.78

Lorraine

0.75

 Cana

0.73

 Waterloo

0.71

 Keegan

0.68

Waterloo

0.68

 Melton

0.67

 Dora

0.66

Puy

0.66

Activations Density 1.892%

terms related to patient care interventions and characteristics

No Comments

No Known Activations