INDEX

Explanations

mentions of patent-related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to patents and patent applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

de

-0.70

 Revel

-0.69

ombies

-0.68

ashington

-0.66

 Lans

-0.65

 Isles

-0.65

 Helpful

-0.65

akening

-0.65

esta

-0.63

regon

-0.62

POSITIVE LOGITS

 infringement

0.98

 patent

0.94

 patents

0.92

 portfolio

0.87

enced

0.85

ability

0.79

 Patent

0.79

ulent

0.77

 licensing

0.77

ellectual

0.75

Activations Density 0.014%

mentions of patent-related terms

terms related to patents and patent applications

No Comments

No Known Activations