INDEX

Explanations

segments of code or comments within programming documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 <=",

-0.64

 defaultstate

-0.63

 &___

-0.61

 незавершена

-0.60

 cakes

-0.58

 cake

-0.58

 henvisninger

-0.57

wesenheit

-0.56

Caz

-0.55

endphp

-0.54

POSITIVE LOGITS

/*

0.76

 发表于

0.63

SuppressMessage

0.62

GeneratedMessage

0.60

riwal

0.59

CloseOperation

0.56

 himſelf

0.56

<blockquote>

0.54

اشت

0.53

 Перейти

0.53

Activations Density 0.094%

segments of code or comments within programming documents

No Comments

No Known Activations