INDEX

Explanations

mentions of monopolies

oai_token-act-pair · gpt-3.5-turbo

references to monopolies and their implications

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

burn

-0.74

older

-0.74

gnu

-0.74

irling

-0.69

den

-0.68

adows

-0.68

travel

-0.67

hur

-0.67

itch

-0.66

di

-0.64

POSITIVE LOGITS

 monopoly

1.20

 monopol

1.11

ategory

0.91

opoly

0.91

ensable

0.86

ulence

0.83

eers

0.80

opol

0.77

ulent

0.75

 mentality

0.74

Activations Density 0.022%

mentions of monopolies

references to monopolies and their implications

No Comments

No Known Activations