INDEX

Explanations

numeric values indicating significance or urgency

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

time +

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

出版年

-0.82

iſten

-0.73

iſter

-0.70

AddHtmlAttribute

-0.65

SequentialGroup

-0.63

 متعلقه

-0.61

ロウィン

-0.60

 ſei

-0.59

ésultats

-0.58

richTextPanel

-0.58

POSITIVE LOGITS

 liền

0.34

randomUUID

0.34

הערות

0.32

 Independencia

0.32

null

0.32

 Roskov

0.32

 Comunicación

0.31

Conclusión

0.31

 TIEMPO

0.31

ピール

0.31

Activations Density 0.070%

numeric values indicating significance or urgency

time +

No Comments

No Known Activations

numeric values indicating significance or urgency

time +

No Comments

No Known Activations