INDEX

Explanations

specific numerical values within structured data

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

Followed by non-English characters or symbols

np_acts-logits-general · gemini-2.0-flash

Whitney test

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

+#+#

-0.90

 lenker

-0.87

AndEndTag

-0.86

bootstrapcdn

-0.85

 חיצוניים

-0.77

 Hamlin

-0.74

IsContent

-0.73

zzleHttp

-0.73

EndProject

-0.71

GenerationType

-0.68

POSITIVE LOGITS

1.11

⒎

0.54

0.48

mainAxisSize

0.48

ระ

0.46

0.44

raš

0.44

al

0.43

⑦

0.43

Activations Density 0.045%

specific numerical values within structured data

Followed by non-English characters or symbols

Whitney test

No Comments

No Known Activations