INDEX

Explanations

instructional phrases guiding through processes or tasks

oai_token-act-pair · gpt-3.5-turbo

instructional content focused on tutorials and guidance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

soType

-0.90

 Crosby

-0.77

 vetoed

-0.72

 plaint

-0.71

 Rasmussen

-0.71

 resent

-0.69

 outp

-0.68

 Gallup

-0.67

poll

-0.67

eous

-0.66

POSITIVE LOGITS

 tutorials

1.42

 basics

1.39

 tutorial

1.37

 Basics

1.35

 Tutorial

1.32

Introduction

1.30

utorial

1.29

 Introduction

1.24

 Begin

1.23

 beginner

1.22

Activations Density 0.480%

instructional phrases guiding through processes or tasks

instructional content focused on tutorials and guidance

No Comments

No Known Activations