INDEX

Explanations

punctuation marks, particularly quotes and parentheses, indicating dialogue or citations

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

+#+#

-0.69

/</

-0.53

 estekak

-0.51

-0.50

kam

-0.49

/−

-0.48

driver

-0.48

};*/

-0.48

 film

-0.47

Дорогие

-0.47

POSITIVE LOGITS

 Roskov

0.69

 stanovnika

0.65

 trypsin

0.64

 "...

0.60

 buckwheat

0.59

 unittest

0.58

Бахар

0.57

 linkovi

0.57

 Vikipedi

0.57

 endblock

0.57

Activations Density 0.246%

punctuation marks, particularly quotes and parentheses, indicating dialogue or citations

No Comments

No Known Activations