INDEX

Explanations

variations of the word "Gri" or its derivatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AndEndTag

-0.72

jsdelivr

-0.71

 autorytatywna

-0.67

 EClass

-0.66

Obrázky

-0.66

Espèce

-0.66

scrapy

-0.57

bootstrapcdn

-0.56

 ویکی‌پدیا

-0.55

RotationOrder

-0.54

POSITIVE LOGITS

Gri

0.93

Gri

0.85

gr

0.76

gri

0.74

GR

0.73

Gr

0.70

Gr

0.70

 Gris

0.69

Gris

0.69

はじめに

0.67

Activations Density 0.056%

variations of the word "Gri" or its derivatives

No Comments

No Known Activations