INDEX

Explanations

headings or titles labeled as "Introduction"

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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rone

-0.79

rage

-0.70

yss

-0.67

 saline

-0.66

riter

-0.65

 opio

-0.64

rio

-0.64

rogens

-0.62

 enthus

-0.62

rock

-0.62

POSITIVE LOGITS

xual

0.80

ptions

0.80

spection

0.76

 Introduction

0.72

 thereto

0.71

>[

0.71

prise

0.71

 Takeru

0.70

APR

0.70

ãħĭãħĭ

0.70

Activations Density 0.010%

headings or titles labeled as "Introduction"

instances of the word "Introduction."

No Comments

No Known Activations