INDEX

Explanations

mentions of books or related terms

oai_token-act-pair · gpt-3.5-turbo

mentions of books

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

00200000

-0.76

 Security

-0.69

ntil

-0.67

alty

-0.67

 Bots

-0.67

Yin

-0.65

 Normandy

-0.65

asonic

-0.64

 Vital

-0.63

ple

-0.62

POSITIVE LOGITS

stores

1.32

hel

1.09

books

1.04

worms

1.01

marks

1.01

shop

1.01

seller

0.94

 books

0.93

chin

0.92

poons

0.91

Activations Density 0.035%

mentions of books or related terms

mentions of books

No Comments

No Known Activations