INDEX

Explanations

terms and references related to gaming or game mechanics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.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

dro

-0.47

...

-0.45

HandleFunc

-0.43

cere

-0.43

dro

-0.41

 prote

-0.41

ValueStyle

-0.41

ms

-0.41

 estre

-0.41

 '\\;'

-0.40

POSITIVE LOGITS

 للاسماء

0.82

 ویکی‌پدیای

0.81

Personendaten

0.81

 незавершена

0.76

 secondaires

0.72

 continúas

0.72

🇶

0.71

 Baillargeon

0.68

GEBURTS

0.68

 AssemblyProduct

0.67

Activations Density 1.282%

terms and references related to gaming or game mechanics

No Comments

No Known Activations