INDEX

Explanations

specific references to entities or organizations

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

<start_of_turn>user

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

 ✭✭

-0.40

ttemberg

-0.39

IUrlHelper

-0.38

новниш

-0.38

catid

-0.36

withOpacity

-0.35

…

-0.35

gyű

-0.35

}$}

-0.35

 forgive

-0.35

POSITIVE LOGITS

 estekak

0.56

 ویکی‌پدی

0.55

 Taktlose

0.53

下载附件

0.53

ValueGenerated

0.52

 Wiktionnaire

0.50

tagHelperRunner

0.50

 فريبيس

0.50

Portale

0.49

 BytesLike

0.48

Activations Density 0.000%

specific references to entities or organizations

<start_of_turn>user

No Comments

No Known Activations