INDEX

Explanations

words related to burglary and theft

oai_token-act-pair · gpt-3.5-turbo

terms related to burglary and theft

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

SHIP

-0.85

usha

-0.81

utical

-0.81

Stage

-0.72

imester

-0.72

shr

-0.70

utics

-0.69

nesota

-0.69

uberty

-0.69

utic

-0.68

POSITIVE LOGITS

 burg

1.35

 burgl

1.26

 burglary

1.14

undy

0.91

 Burg

0.84

 alarms

0.81

lar

0.77

 robbery

0.76

 suspects

0.76

rosse

0.74

Activations Density 0.018%

words related to burglary and theft

terms related to burglary and theft

No Comments

No Known Activations