INDEX

Explanations

pet-related terms

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of people and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

mercial

-0.88

terday

-0.87

xual

-0.80

etheless

-0.76

 absor

-0.72

ĨĴ

-0.72

BILITY

-0.70

vironment

-0.68

successfully

-0.66

sers

-0.65

POSITIVE LOGITS

rick

1.07

hend

0.96

rov

0.95

ras

0.90

alon

0.90

ulia

0.89

raf

0.89

terson

0.89

ley

0.89

rik

0.89

Activations Density 0.127%

pet-related terms

proper nouns, particularly names of people and places

No Comments

No Known Activations