INDEX

Explanations

numerical values or quantities, particularly in technical or mathematical contexts

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

mathematical notation and code formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

oredCriteria

-0.79

 OFDb

-0.73

SharedCtor

-0.67

Jeografia

-0.65

Cyfarwyddwr

-0.64

 Italijani

-0.64

XmlEnum

-0.64

rrggbb

-0.64

 المعيارى

-0.62

Personendaten

-0.61

POSITIVE LOGITS

 kasarigan

0.55

<h1>

0.38

hline

0.36

Còn

0.34

Welcome

0.33

</tr>

0.32

 tapa

0.32

FormatException

0.31

</tbody>

0.31

Activations Density 0.000%

numerical values or quantities, particularly in technical or mathematical contexts

mathematical notation and code formatting

No Comments

No Known Activations