INDEX

Explanations

words related to laws or regulations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'p' within the text

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

 compe

-0.85

 GOODMAN

-0.79

ãĤ´ãĥ³

-0.73

FTWARE

-0.71

 Horizon

-0.71

æ©Ł

-0.70

NESS

-0.69

 Exodus

-0.66

 Resurrection

-0.66

 Demo

-0.65

POSITIVE LOGITS

atern

1.25

uffed

1.24

orters

1.23

ierce

1.20

ussy

1.19

orter

1.18

aired

1.16

okes

1.16

appy

1.15

ardon

1.13

Activations Density 0.037%

words related to laws or regulations

occurrences of the letter 'p' within the text

No Comments

No Known Activations