INDEX

Explanations

instances of plagiarism or related terminology in a text

oai_token-act-pair · gpt-3.5-turbo

terms related to plagiarism and manuscripts

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

ened

-0.89

ega

-0.86

enburg

-0.79

lace

-0.75

ening

-0.74

points

-0.71

 Canary

-0.70

atives

-0.69

wich

-0.68

NEY

-0.68

POSITIVE LOGITS

 plagiar

1.01

ibli

0.86

 manuscript

0.83

 manuscripts

0.82

lishing

0.81

uscript

0.79

 notebooks

0.76

urs

0.75

 muse

0.73

translation

0.73

Activations Density 0.036%

instances of plagiarism or related terminology in a text

terms related to plagiarism and manuscripts

No Comments

No Known Activations

instances of plagiarism or related terminology in a text

terms related to plagiarism and manuscripts

No Comments

No Known Activations