INDEX

Explanations

proper nouns related to geographical locations, organizations, and events

oai_token-act-pair · gpt-3.5-turbo

references to specific institutions and geographical locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

•isco

#4 activation: 9.19

No Comments

Negative Logits

yond

-0.73

sit

-0.66

every

-0.65

because

-0.65

whatever

-0.64

 destro

-0.64

who

-0.62

 predec

-0.61

 advoc

-0.61

those

-0.61

POSITIVE LOGITS

 âĵĺ

1.10

 Overview

1.00

 Transcript

0.90

 Highlights

0.88

Â¶

0.88

 Introduction

0.88

 Locations

0.86

 Description

0.85

 Background

0.85

Activations Density 0.518%

proper nouns related to geographical locations, organizations, and events

references to specific institutions and geographical locations

No Comments

No Known Activations