INDEX

Explanations

technical terms and structures related to programming, specifically in the context of threading and data handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 تضيفلها

-0.33

hi

-0.30

 nons

-0.27

sample

-0.26

 whistle

-0.25

Ljava

-0.24

 local

-0.24

li

-0.24

top

-0.23

POSITIVE LOGITS

 resourceCulture

0.77

DockStyle

0.77

 zwiſchen

0.74

 ſind

0.73

parsedMessage

0.73

دانشنامهٔ

0.70

 Administrativna

0.69

ſammen

0.69

 zuſammen

0.68

VYMaps

0.67

Activations Density 1.431%

technical terms and structures related to programming, specifically in the context of threading and data handling

No Comments

No Known Activations