INDEX

Explanations

verbs related to actions and events in reports or documentation

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

followed by prepositions

np_acts-logits-general · gemini-2.0-flash

past events and their context

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

 miniaturka

-0.39

 ویکی‌پدی

-0.37

 mitään

-0.37

 Presidencia

-0.36

 Führung

-0.35

 краї

-0.34

zieży

-0.33

 země

-0.32

 Beschwerden

-0.32

 dormitórios

-0.32

POSITIVE LOGITS

AndEndTag

0.69

OGND

0.68

SBATCH

0.65

basicConfig

0.65

 consultato

0.63

 abgerufen

0.62

DockStyle

0.60

 فريبيس

0.60

 مواليد

0.60

 Chwiliwch

0.59

Activations Density 1.399%

verbs related to actions and events in reports or documentation

followed by prepositions

past events and their context

No Comments

No Known Activations