INDEX

Explanations

numerical values related to statistics or measurements

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

Bronnen

-0.84

出版年

-0.73

 كومونز

-0.72

uesa

-0.66

utiva

-0.64

 adipis

-0.62

Vaya

-0.61

 Bres

-0.61

})}

-0.61

tehenden

-0.61

POSITIVE LOGITS

ValueStyle

0.69

ichè

0.67

 distanciation

0.67

 TextAppearance

0.59

aarrggbb

0.57

Portail

0.56

ViewInit

0.55

errHandler

0.54

TintMode

0.54

 yearly

0.54

Activations Density 0.396%

numerical values related to statistics or measurements

No Comments

No Known Activations