INDEX

Explanations

mathematical or technical notations

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

Tokens before math symbols

np_acts-logits-general · gemini-2.0-flash

verbs indicating continuation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 giapponese

-0.50

Username

-0.49

Độ

-0.48

posts

-0.48

❋

-0.48

pillar

-0.45

enedor

-0.45

 död

-0.45

eczka

-0.44

 semicolon

-0.44

POSITIVE LOGITS

InputBorder

0.74

 StatefulWidget

0.71

 doInBackground

0.68

 kasarigan

0.68

XmlAccessType

0.67

 showcase

0.62

 mingle

0.62

 StatelessWidget

0.62

RectangleBorder

0.61

มาะ

0.60

Activations Density 0.174%

mathematical or technical notations

Tokens before math symbols

verbs indicating continuation

No Comments

No Known Activations