INDEX

Explanations

words related to criminal activities, particularly burglary

oai_token-act-pair · gpt-3.5-turbo

terms related to burglary and related criminal activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

utical

-0.75

usha

-0.71

utic

-0.70

itarian

-0.70

shr

-0.69

aeda

-0.68

SHIP

-0.68

boa

-0.67

itism

-0.67

 Nadu

-0.66

POSITIVE LOGITS

 burg

1.14

 burgl

1.04

lar

0.97

 burglary

0.92

undy

0.91

 Burg

0.74

 alarms

0.74

hers

0.72

kered

0.71

bats

0.69

Activations Density 0.030%

words related to criminal activities, particularly burglary

terms related to burglary and related criminal activities

No Comments

No Known Activations