INDEX

Explanations

company or organization names

oai_token-act-pair · gpt-3.5-turbo

indicators of social media engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 interven

-0.69

sic

-0.69

 estab

-0.67

ichick

-0.65

ãĤ©

-0.65

 reper

-0.63

 unsuccessful

-0.62

etheless

-0.61

 appe

-0.59

 thwarted

-0.59

POSITIVE LOGITS

Disclaimer

0.81

Synopsis

0.81

 SHARES

0.79

Product

0.78

Introduction

0.78

Researchers

0.78

Overview

0.77

WASHINGTON

0.76

Welcome

0.76

Posted

0.75

Activations Density 0.167%

company or organization names

indicators of social media engagement

No Comments

No Known Activations