INDEX

Explanations

expressions that specify inquiries or statements about identity or existence

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

"That's what"

np_acts-logits-general · gemini-2.0-flash

that's what clauses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 كومونز

-0.48

addContainerGap

-0.47

borderSide

-0.44

}{*}{}

-0.41

 الدولى

-0.39

 الحره

-0.39

 évent

-0.38

CloseOperation

-0.38

ungo

-0.37

PRNewswire

-0.37

POSITIVE LOGITS

 worauf

0.52

こそ

0.50

hrens

0.46

FontOfSize

0.46

stylers

0.45

Πηγές

0.45

 آنچه

0.45

jupiter

0.44

 Именно

0.43

VersionUID

0.43

Activations Density 0.109%

expressions that specify inquiries or statements about identity or existence

"That's what"

that's what clauses

No Comments

No Known Activations