INDEX

Explanations

mathematical or scientific notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 aikaa

-0.63

ReusableCell

-0.58

memberOf

-0.51

zają

-0.47

 sienta

-0.46

ButterKnife

-0.45

 sonda

-0.44

 kív

-0.44

ngilizce

-0.43

Oui

-0.43

POSITIVE LOGITS

 million

1.15

 Millions

1.13

 millions

1.11

Millions

1.06

Million

0.99

millions

0.99

 Million

0.98

 MILLION

0.97

 crore

0.97

 millioner

0.97

Activations Density 0.697%

mathematical or scientific notation

No Comments

No Known Activations