INDEX

Explanations

word sequences related to legal agreements and terms

oai_token-act-pair · gpt-3.5-turbo

legal terms and agreements related to licensing and compliance

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

arthed

-0.68

 carbs

-0.67

oldown

-0.67

 grains

-0.66

tun

-0.66

cone

-0.66

ploy

-0.64

amina

-0.64

itiveness

-0.63

 Meng

-0.63

POSITIVE LOGITS

 disclaim

0.94

 Privacy

0.94

olicited

0.87

 trademarks

0.83

 Regist

0.83

 Seller

0.83

 disclaimer

0.83

 Terms

0.82

 herein

0.82

 hereby

0.82

Activations Density 0.375%

word sequences related to legal agreements and terms

legal terms and agreements related to licensing and compliance

No Comments

No Known Activations