INDEX

Explanations

mathematical expressions related to dimensions, projections, and set theory operations

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

Mathematical or symbolic expressions

np_acts-logits-general · gemini-2.0-flash

mathematical superscripts (P^)

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

="@+

-0.69

 iprot

-0.65

APORE

-0.64

uxxxx

-0.63

AddHtmlAttribute

-0.60

期刊论文

-0.59

-------------</

-0.58

 ویکی‌پدی

-0.58

Slf

-0.58

دانشنامهٔ

-0.58

POSITIVE LOGITS

Tembelea

0.62

SharedCtor

0.61

ConstraintMaker

0.54

stanze

0.47

ëren

0.47

inspace

0.46

بالإنجليزية

0.46

{},

0.45

存于互联网档案馆

0.45

WithIOException

0.45

Activations Density 1.747%

mathematical expressions related to dimensions, projections, and set theory operations

Mathematical or symbolic expressions

mathematical superscripts (P^)

No Comments

No Known Activations