INDEX

Explanations

phrases related to legal offenses and crimes

oai_token-act-pair · gpt-3.5-turbo

terms related to legal violations and offenses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

quickShipAvailable

-0.90

achev

-0.76

NetMessage

-0.70

VIS

-0.69

soDeliveryDate

-0.67

visors

-0.66

 artificial

-0.66

flush

-0.65

SUP

-0.65

UNCH

-0.65

POSITIVE LOGITS

 punishable

1.47

 committed

1.30

 perpetrated

1.15

 spree

1.08

 offences

1.01

 prosecuted

0.98

 against

0.97

 involving

0.96

 indict

0.95

 convictions

0.94

Activations Density 0.074%

phrases related to legal offenses and crimes

terms related to legal violations and offenses

No Comments

No Known Activations