INDEX

Explanations

the word "tens" followed by any number

oai_token-act-pair · gpt-3.5-turbo

phrases related to large quantities of people or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Shrine

-0.64

mint

-0.64

 Colony

-0.64

agate

-0.63

 Boards

-0.60

 Manifest

-0.60

 commentary

-0.60

adv

-0.59

 Slayer

-0.59

 messenger

-0.58

POSITIVE LOGITS

omet

1.00

eteen

0.99

ourcing

0.97

elfth

0.96

atile

0.96

eenth

0.95

imet

0.92

eteenth

0.90

umbing

0.87

atility

0.87

Activations Density 0.013%

the word "tens" followed by any number

phrases related to large quantities of people or items

No Comments

No Known Activations