INDEX

Explanations

positive phrases and descriptors about an experience or item

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

ValueStyle

-0.60

EndInit

-0.51

 bowiem

-0.48

 namelijk

-0.48

Ссылки

-0.48

 سكانية

-0.47

("*");

-0.45

Crop

-0.45

 totiž

-0.45

labus

-0.44

POSITIVE LOGITS

RectangleBorder

0.86

AddHtmlAttribute

0.82

XmlAccessorType

0.72

ArrowToggle

0.71

 noqa

0.68

 disjoint

0.67

DataAnnotations

0.66

 snippetHide

0.64

RefNanny

0.62

 SwiftUI

0.61

Activations Density 0.820%

positive phrases and descriptors about an experience or item

No Comments

No Known Activations