INDEX

Explanations

phrases indicating rules, permissions, or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 الحره

-0.56

 mẽ

-0.50

 abat

-0.50

 profondément

-0.47

 विश्वसनीयता

-0.47

 orar

-0.46

bihi

-0.45

ilarities

-0.45

publicain

-0.45

 rendent

-0.45

POSITIVE LOGITS

 unknownFields

0.73

 viewType

0.70

GOTREF

0.64

 оригіналу

0.62

MultipartFile

0.62

MessageOf

0.62

expandindo

0.60

ाहरण

0.59

StoreMessageInfo

0.59

ImageContext

0.59

Activations Density 0.411%

phrases indicating rules, permissions, or conditions

No Comments

No Known Activations