INDEX

Explanations

technical terms and instructions related to software development and programming

oai_token-act-pair · gpt-3.5-turbo

content that outlines processes or tutorials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Loch

-0.73

 Kills

-0.72

 Allies

-0.70

 Guam

-0.69

 Canaveral

-0.65

 Crimson

-0.64

Cyn

-0.63

 Typhoon

-0.63

Alert

-0.63

 Moody

-0.63

POSITIVE LOGITS

posium

0.89

escription

0.88

Introduction

0.88

ĨĴ

0.85

endix

0.84

 discuss

0.82

ocused

0.82

strate

0.81

 assume

0.81

Materials

0.81

Activations Density 0.288%

technical terms and instructions related to software development and programming

content that outlines processes or tutorials

No Comments

No Known Activations