INDEX

Explanations

mathematical or programming symbols and notation

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

الإنجليزية

-0.78

 lenker

-0.64

 '\\;'

-0.63

abestanden

-0.60

 betweenstory

-0.59

 kaarangay

-0.58

 estekak

-0.58

Спасылкі

-0.55

 Meksiku

-0.53

UnsafeEnabled

-0.52

POSITIVE LOGITS

ритори

0.53

allos

0.50

رج

0.48

irchen

0.46

rantz

0.44

WSTR

0.43

ließlich

0.43

 fold

0.43

丫

0.43

cusa

0.42

Activations Density 0.577%

mathematical or programming symbols and notation

No Comments

No Known Activations