INDEX

Explanations

phrases emphasizing the capability or possibility of performing a task

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

"able to"

np_acts-logits-general · gemini-2.0-flash

texts containing 'able to'

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

>--}}

-0.60

encils

-0.58

Packard

-0.58

 Triassic

-0.57

KURZBESCHREIBUNG

-0.57

haviors

-0.56

};*/

-0.56

 voorwaarden

-0.56

ffion

-0.55

>"+

-0.54

POSITIVE LOGITS

MigrationBuilder

0.71

 المعيارى

0.58

 bodied

0.58

 estekak

0.54

GEBURTSDATUM

0.52

ReusableCell

0.49

usercontent

0.48

venidos

0.47

tamaan

0.47

таратура

0.46

Activations Density 0.071%

phrases emphasizing the capability or possibility of performing a task

"able to"

texts containing 'able to'

No Comments

No Known Activations