INDEX

Explanations

instances of the word "per" indicating measurements or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

}">

-0.57

LEADING

-0.57

eventbus

-0.54

信

-0.52

“

-0.52

WriteLine

-0.51

 acto

-0.51

lý

-0.51

Vir

-0.50

 Werk

-0.50

POSITIVE LOGITS

IsMutable

0.91

 nahilalakip

0.84

HasForeignKey

0.80

 invokingState

0.79

 CreateTagHelper

0.78

ItemBackground

0.78

 propOrder

0.76

Hentet

0.74

 preocupes

0.74

 ویکی‌پدیای

0.73

Activations Density 0.088%

instances of the word "per" indicating measurements or quantities

No Comments

No Known Activations