INDEX

Explanations

words or phrases ending with 'p' followed by a numerical value

oai_token-act-pair · gpt-3.5-turbo

instances of the letter 'p'

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

NESS

-0.82

 warr

-0.76

 Lauder

-0.76

æ©Ł

-0.73

 GOODMAN

-0.73

 Palest

-0.72

MpServer

-0.70

 GEAR

-0.69

 Leilan

-0.68

æ©

-0.66

POSITIVE LOGITS

ossible

1.36

resents

1.33

airs

1.27

ulse

1.27

redict

1.27

ilot

1.26

ixels

1.22

ussy

1.21

ushing

1.21

ossession

1.21

Activations Density 0.032%

words or phrases ending with 'p' followed by a numerical value

instances of the letter 'p'

No Comments

No Known Activations