INDEX

Explanations

legal terms and courtroom-related phrases

oai_token-act-pair · gpt-3.5-turbo

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ultural

-0.77

bred

-0.76

obyl

-0.75

-0.73

iquette

-0.72

Quantity

-0.71

oneliness

-0.71

perture

-0.71

 Bulgar

-0.69

ankind

-0.67

POSITIVE LOGITS

 attorneys

1.51

 attorney

1.34

 suing

1.31

 appellate

1.29

 lawyers

1.27

 litigation

1.26

 filings

1.26

 court

1.23

 filed

1.22

sue

1.22

Activations Density 0.619%

legal terms and courtroom-related phrases

No Comments

No Known Activations