INDEX

Explanations

phrases related to quitting a job or habit

oai_token-act-pair · gpt-3.5-turbo

instances of the word "quit."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inen

-0.78

Catalog

-0.77

arov

-0.73

ANS

-0.69

Herm

-0.66

OTH

-0.65

arthy

-0.65

 ancest

-0.63

 GOODMAN

-0.62

ean

-0.62

POSITIVE LOGITS

 smoking

1.15

ting

1.00

 Smoking

1.00

ters

0.98

 Quit

0.94

 quitting

0.85

smoking

0.82

 whining

0.77

 abruptly

0.73

 eating

0.72

Activations Density 0.018%

phrases related to quitting a job or habit

instances of the word "quit."

No Comments

No Known Activations