INDEX

Explanations

content related to programming and API structures

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

Code preceded by "@" or "with"

np_acts-logits-general · gemini-2.0-flash

with self

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

VersionUID

-0.63

scriptcase

-0.61

PrototypeOf

-0.61

ніципа

-0.61

TemporalType

-0.57

bootstrapcdn

-0.57

 Srivastava

-0.55

abetes

-0.54

inerary

-0.53

OnInit

-0.52

POSITIVE LOGITS

AxisAlignment

0.56

GEBURTSDATUM

0.54

出版年

0.49

 Melody

0.49

WithError

0.48

Personensuche

0.48

malige

0.48

ContentAsync

0.47

 Nash

0.46

iest

0.46

Activations Density 0.053%

content related to programming and API structures

Code preceded by "@" or "with"

with self

No Comments

No Known Activations