INDEX

Explanations

key indicators and expressions related to time and temporal reference

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

date, time, or numbers

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



-0.71

TagMode

-0.70

 وتسجيلات

-0.67

 AssemblyCompany

-0.65

 الرياضيه

-0.62

 HasFactory

-0.62

AccessFile

-0.62

 betweenstory

-0.61

 تضيفلها

-0.61



-0.60

POSITIVE LOGITS

 eenvou

0.26

 माल

0.24

 kimse

0.23

///</

0.23

 الآ

0.23

ⓧ

0.23

Do

0.22

 önem

0.21

Simple

0.21

 bowiem

0.21

Activations Density 0.017%

key indicators and expressions related to time and temporal reference

date, time, or numbers

No Comments

No Known Activations