INDEX

Explanations

legal terms and legislative language related to laws and regulations

oai_token-act-pair · gpt-3.5-turbo

mentions of legal or legislative terms and provisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

nit

-0.84

Nintendo

-0.79

 Leica

-0.78

tu

-0.77

Ub

-0.76

 Quadro

-0.75

uni

-0.75

 Seymour

-0.72

Planet

-0.72

leon

-0.71

POSITIVE LOGITS

 legislation

1.74

 bill

1.68

 bills

1.42

 amendment

1.41

 Legislation

1.40

 repeal

1.38

 amendments

1.37

 legislative

1.31

 provisions

1.26

 statute

1.23

Activations Density 0.259%

legal terms and legislative language related to laws and regulations

mentions of legal or legislative terms and provisions

No Comments

No Known Activations