INDEX

Explanations

terms related to patents and patent-related activities

oai_token-act-pair · gpt-3.5-turbo

mentions of patents and related concepts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ombies

-0.73

de

-0.69

 Lans

-0.68

alid

-0.66

avez

-0.66

 Helpful

-0.64

 Prepare

-0.63

sam

-0.63

 sober

-0.62

 Angels

-0.62

POSITIVE LOGITS

 patents

1.16

 patent

1.15

 infringement

0.93

 Patent

0.92

yright

0.85

ulent

0.83

ellectual

0.83

onomy

0.77

urable

0.75

 examiner

0.75

Activations Density 0.009%

terms related to patents and patent-related activities

mentions of patents and related concepts

No Known Activations