INDEX

Explanations

references to various types of publications, specifically magazines and newspapers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

出版年

-0.83

دانشنامهٔ

-0.75

"]();

-0.73

 متعلقه

-0.70

 дописавши

-0.69

Hochspringen

-0.68

SBATCH

-0.67

twimg

-0.65

 CURIAM

-0.65

脚注の使い方

-0.63

POSITIVE LOGITS

0.78

 called

0.75

“

0.71

 denominada

0.67

 denominado

0.67

 geslacht

0.65

 llamada

0.65

0.64

‘

0.60

called

0.58

Activations Density 0.559%

references to various types of publications, specifically magazines and newspapers

No Comments

No Known Activations