INDEX

Explanations

the name "Milo Yiannopoulos"

oai_token-act-pair · gpt-3.5-turbo

mentions of specific individuals, particularly controversial figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

OTS

-0.74

illard

-0.72

redo

-0.71

arist

-0.69

awks

-0.68

abies

-0.66

itness

-0.66

wives

-0.66

incarn

-0.64

yrinth

-0.64

POSITIVE LOGITS

 Yiannopoulos

1.63

iannopoulos

1.08

 Milo

0.97

olini

0.86

 Breitbart

0.84

ullah

0.80

itbart

0.77

 Byrne

0.76

ollah

0.76

 Fowler

0.73

Activations Density 0.009%

the name "Milo Yiannopoulos"

mentions of specific individuals, particularly controversial figures

No Comments

No Known Activations