INDEX

Explanations

phrases related to alertness and alarm settings

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

 Lorraine

-0.80

Puy

-0.72

 Waterloo

-0.72

 Cana

-0.71

Waterloo

-0.67

Lorraine

-0.66

AndEndTag

-0.64

DCM

-0.64

 Melton

-0.64

 Dray

-0.63

POSITIVE LOGITS

σ

0.99

 Riley

0.97

Ali

0.92

σ

0.90

sigma

0.87

 Williams

0.86

 Varela

0.83

Ali

0.83

Riley

0.83

 sigma

0.80

Activations Density 1.082%

phrases related to alertness and alarm settings

No Comments

No Known Activations