INDEX

Explanations

author attribution in a text

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

phrases indicating authorship or attribution in written content

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

itives

-0.82

Finish

-0.72

isable

-0.68

Ø§ÙĦ

-0.67

vation

-0.67

SPONSORED

-0.64

ioxide

-0.64

MpServer

-0.62

Insp

-0.60

 pains

-0.58

POSITIVE LOGITS

akuya

1.08

 contrast

0.96

 Hilbert

0.86

 virtue

0.83

stand

0.81

pass

0.78

catch

0.75

tes

0.73

tom

0.73

ron

0.72

Activations Density 0.029%

author attribution in a text

phrases indicating authorship or attribution in written content

No Comments

No Known Activations