INDEX

Explanations

words and phrases related to political incidents and official responses

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

after certain prepositions or articles

np_acts-logits-general · gemini-2.0-flash

locations and places

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

 متعلقه

-0.76

 smtplib

-0.62

ONESIA

-0.58

LEncoder

-0.57

ConstraintMaker

-0.56

 histone

-0.55

KommentareTeilen

-0.54

 NSCoder

-0.52

Välislingid

-0.52

 utafiti

-0.52

POSITIVE LOGITS

 nakalista

0.55

 оригіналу

0.52

 StatefulWidget

0.51

]**

0.51

});*/

0.50

sero

0.50

Along

0.50

 Along

0.49

ScopeManager

0.48

 Paglinawan

0.47

Activations Density 0.067%

words and phrases related to political incidents and official responses

after certain prepositions or articles

locations and places

No Comments

No Known Activations