INDEX

Explanations

keywords related to introductions or initiating content

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Introduction."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

rone

-0.84

rage

-0.74

rett

-0.73

rie

-0.72

ief

-0.69

riter

-0.68

roph

-0.65

rice

-0.65

 saline

-0.65

 opio

-0.65

POSITIVE LOGITS

matter

0.87

 thereto

0.86

spection

0.85

gdala

0.76

xual

0.74

regor

0.72

 Introduction

0.71

uador

0.69

 Pione

0.69

APR

0.68

Activations Density 0.028%

keywords related to introductions or initiating content

instances of the word "Introduction."

No Comments

No Known Activations