INDEX

Explanations

phrases related to legal documents and agreements

oai_token-act-pair · gpt-3.5-turbo

references to specific entities or regulations related to a legal or organizational context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

=""

-0.72

igans

-0.70

LOD

-0.68

tackle

-0.67

Bloomberg

-0.66

 hardly

-0.66

pher

-0.64

AH

-0.64

 billionaires

-0.63

 wisely

-0.63

POSITIVE LOGITS

 purchaser

1.29

 licensee

1.25

 respective

1.24

 applicant

1.20

 same

1.18

 foregoing

1.14

 remainder

1.12

 highest

1.12

 complainant

1.12

 defendant

1.10

Activations Density 0.726%

phrases related to legal documents and agreements

references to specific entities or regulations related to a legal or organizational context

No Comments

No Known Activations