INDEX

Explanations

technical terms related to software development and tutorials

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a discussion or tutorial format

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Allies

-0.76

 Loch

-0.73

 havoc

-0.63

 Izan

-0.63

 Mechdragon

-0.63

 Planes

-0.62

['

-0.61

 Lobby

-0.60

 Andromeda

-0.59

Mn

-0.59

POSITIVE LOGITS

escription

0.92

endix

0.90

 Sketch

0.85

 excerpt

0.84

Introduction

0.82

fter

0.81

isode

0.80

 excerpts

0.77

posium

0.77

 illustrate

0.76

Activations Density 0.622%

technical terms related to software development and tutorials

phrases indicating a discussion or tutorial format

No Comments

No Known Activations