INDEX

Explanations

references to different modes or settings in a system

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

springframework

-0.73

?>

-0.67

************

-0.66

 methyl

-0.65

fetch

-0.65

///</

-0.62

'){

-0.62

 "'");

-0.62

xss

-0.60

addContainerGap

-0.60

POSITIVE LOGITS

 Mode

2.54

 mode

2.43

mode

2.42

Mode

2.36

 modes

2.31

 MODE

2.28

modes

2.22

 Modes

2.22

MODE

2.10

Modes

2.07

Activations Density 0.051%

references to different modes or settings in a system

No Comments

No Known Activations