INDEX

Explanations

phrases related to economic development and disparities between developed and developing countries

oai_token-act-pair · gpt-3.5-turbo

references to economic classifications of countries, specifically "developed" and "developing" nations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

potion

-0.83

nown

-0.78

ADRA

-0.75

ograp

-0.75

inventoryQuantity

-0.75

Accessory

-0.74

assador

-0.74

elight

-0.74

ãĤ´ãĥ³

-0.72

ATURES

-0.71

POSITIVE LOGITS

 countries

1.16

 nations

1.15

 industrialized

1.15

 coastal

1.13

 regions

1.11

 counties

1.10

 suburbs

1.10

 provinces

1.08

 towns

1.05

 rural

1.05

Activations Density 0.262%

phrases related to economic development and disparities between developed and developing countries

references to economic classifications of countries, specifically "developed" and "developing" nations

No Comments

No Known Activations