INDEX

Explanations

mothers with specific family characteristics

oai_token-act-pair · gpt-3.5-turbo

phrases indicating familial relationships, particularly focusing on mothers and their children

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

krit

-0.87

BIL

-0.73

Contract

-0.72

soDeliveryDate

-0.71

OVER

-0.71

 Archdemon

-0.70

issions

-0.69

HUD

-0.68

FW

-0.67

Dialog

-0.67

POSITIVE LOGITS

 grandparents

0.87

thood

0.82

 daughters

0.81

 grandmother

0.81

 elder

0.80

 sons

0.78

 children

0.77

 twins

0.77

 deceased

0.75

gio

0.74

Activations Density 0.098%

mothers with specific family characteristics

phrases indicating familial relationships, particularly focusing on mothers and their children

No Comments

No Known Activations