INDEX

Explanations

words related to luxury and lavishness

oai_token-act-pair · gpt-3.5-turbo

references to the term "lavish" and its variations, indicating opulence or excessive wealth

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

Ĥª

-0.72

sein

-0.68

roads

-0.67

POS

-0.67

figure

-0.67

PRES

-0.67

PDATE

-0.66

BOOK

-0.66

Christ

-0.65

change

-0.64

POSITIVE LOGITS

ishly

1.08

iolet

1.04

endar

1.04

Lav

1.02

atories

1.01

igne

0.95

atory

0.92

adium

0.92

anca

0.90

acy

0.89

Activations Density 0.016%

words related to luxury and lavishness

references to the term "lavish" and its variations, indicating opulence or excessive wealth

No Comments

No Known Activations