INDEX

Explanations

structured formats and metadata tags used in coding or programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 itſelf

-1.05

 ―――――

-0.94

 myſelf

-0.85

تقاوى

-0.85

 iſt

-0.85

 himſelf

-0.84

 المعرف

-0.84

AsUp

-0.83

 Anſ

-0.81

+#+

-0.80

POSITIVE LOGITS

gemäß

0.67

 Duncan

0.61

$_['

0.61

↵↵

0.60

しくは

0.60

"]=

0.59

the

0.59

The

0.57

);?>

0.56

ivar

0.56

Activations Density 0.385%

structured formats and metadata tags used in coding or programming contexts

No Comments

No Known Activations