INDEX

Explanations

references to the prefix "hy" related to specific scientific contexts or terminologies

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

Tokens starting with "hy"

np_acts-logits-general · gemini-2.0-flash

hy followed by words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 AssemblyCulture

-0.66

webElementXpaths

-0.56

InjectAttribute

-0.56

AutoScaleMode

-0.55

日閲覧

-0.55

onActivityResult

-0.51

ípios

-0.49

 movimenti

-0.49

 taban

-0.49

تاب

-0.49

POSITIVE LOGITS

hy

0.65

Hy

0.59

Hy

0.54

SourceChecksum

0.53

schnitt

0.50

 مرئيه

0.50

 Crow

0.49

 drau

0.47

}?>

0.47

+%

0.47

Activations Density 0.178%

references to the prefix "hy" related to specific scientific contexts or terminologies

Tokens starting with "hy"

hy followed by words

No Comments

No Known Activations