INDEX

Explanations

segments indicating the original appearance and reproduction of articles

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the original source or authorship of an article

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

aura

-0.74

gui

-0.73

witch

-0.70

worms

-0.69

tra

-0.68

uka

-0.67

xus

-0.67

gas

-0.67

effect

-0.66

trap

-0.65

POSITIVE LOGITS

 Editorial

0.92

 reprint

0.92

 satire

0.85

 Contribut

0.80

cerpt

0.79

 reprinted

0.76

 editorial

0.75

 Published

0.74

 reader

0.74

 unpublished

0.73

Activations Density 0.491%

segments indicating the original appearance and reproduction of articles

phrases indicating the original source or authorship of an article

No Comments

No Known Activations