INDEX

Explanations

references to imperfections and qualities that add character or charm

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 للاسماء

-0.64

ugou

-0.56

}$

-0.56

''

-0.55

 flammable

-0.50

malink

-0.50

hots

-0.50

 يتيمه

-0.50

主持人

-0.49

НИК

-0.49

POSITIVE LOGITS

 InputDecoration

0.59

AsUp

0.58

Przypisy

0.56

 validamos

0.54

 excus

0.54

 excused

0.51

 SafeMath

0.49

 preuve

0.49

 voulons

0.48

 Happens

0.48

Activations Density 0.352%

references to imperfections and qualities that add character or charm

No Comments

No Known Activations