INDEX

Explanations

annotations and metadata in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

źni

-0.55

-0.51

ksikon

-0.50

criptures

-0.47

carrier

-0.44

 corrida

-0.44

XmlAccessType

-0.44

riers

-0.44

 pajero

-0.43

 cảnh

-0.43

POSITIVE LOGITS

endphp

0.66

SuppressWarnings

0.63

Composable

0.62

@@@@@@@@

0.59

dataclass

0.56

staticmethod

0.56

@@@@@

0.53

SizeF

0.52

SuppressLint

0.52

RISK

0.52

Activations Density 0.247%

annotations and metadata in code

No Comments

No Known Activations