INDEX

Explanations

numerical data and measurements

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

Numerical percentages

np_acts-logits-general · gemini-2.0-flash

numbers and punctuation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

contentLoaded

-0.62

Del

-0.51

mod

-0.51

AVING

-0.50

 Sche

-0.50

 useAppContext

-0.49

apour

-0.49

rika

-0.49

 rules

-0.49

 fall

-0.48

POSITIVE LOGITS

"?>

0.56

 pytest

0.55

 couverte

0.55

 masculinity

0.55

 Escolar

0.55

 Nadie

0.54

 romántico

0.54

 romántica

0.52

HostException

0.52

calientes

0.52

Activations Density 0.452%

numerical data and measurements

Numerical percentages

numbers and punctuation

No Comments

No Known Activations