INDEX

Explanations

terms related to patents and patent applications

oai_token-act-pair · gpt-3.5-turbo

references to patents and patent-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Revel

-0.76

 Isles

-0.73

hani

-0.69

de

-0.67

 Helm

-0.63

ashington

-0.63

Boh

-0.62

Thom

-0.61

 Lans

-0.61

ombies

-0.61

POSITIVE LOGITS

 infringement

0.99

enced

0.88

 patent

0.86

 patents

0.82

 portfolio

0.79

ulent

0.77

 examiner

0.76

onomy

0.75

 filings

0.74

ability

0.73

Activations Density 0.016%

terms related to patents and patent applications

references to patents and patent-related terms

No Comments

No Known Activations