INDEX

Explanations

instances of plagiarism or copying within text

oai_token-act-pair · gpt-3.5-turbo

terms related to plagiarism and copying content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

croft

-0.81

ALE

-0.76

ahime

-0.71

ving

-0.71

alone

-0.68

liner

-0.67

Dispatch

-0.67

ibur

-0.65

eely

-0.65

olutions

-0.64

POSITIVE LOGITS

 copied

1.13

 plagiar

0.87

 copying

0.85

smanship

0.79

xual

0.79

 Gutenberg

0.72

 proced

0.71

 unfocusedRange

0.69

writer

0.67

YR

0.67

Activations Density 0.015%

instances of plagiarism or copying within text

terms related to plagiarism and copying content

No Comments

No Known Activations