INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

references to the letter 'Z' or its associated names

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

tenance

-0.72

espie

-0.71

 Scots

-0.68

ãĥ¼ãĥĨãĤ£

-0.67

croft

-0.67

ãĥ¼ãĥĨ

-0.66

 spirited

-0.64

 acknow

-0.64

 captcha

-0.64

 Lauder

-0.63

POSITIVE LOGITS

ERO

1.28

ebra

1.23

odiac

1.11

eros

1.07

ealous

0.99

ooming

0.99

ymes

0.99

ombies

0.99

immer

0.98

ONE

0.97

Activations Density 0.023%

proper nouns

references to the letter 'Z' or its associated names

No Comments

No Known Activations