INDEX

Explanations

references to social classes, especially the middle class

oai_token-act-pair · gpt-3.5-turbo

references to the middle class

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

TAG

-0.79

Downloadha

-0.77

inventoryQuantity

-0.74

 Archdemon

-0.74

 Mast

-0.67

SCP

-0.67

oldown

-0.67

soDeliveryDate

-0.66

KEY

-0.65

sbm

-0.64

POSITIVE LOGITS

 earners

0.93

 incomes

0.82

ifications

0.73

naire

0.71

ocrats

0.70

 Revival

0.69

 mobility

0.68

 retirees

0.68

 taxp

0.68

 families

0.67

Activations Density 0.018%

references to social classes, especially the middle class

references to the middle class

No Comments

No Known Activations