INDEX

Explanations

phrases related to the Beatitudes

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Beat" or variations of it in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

OPLE

-0.91

 Strat

-0.72

 occas

-0.71

ateral

-0.70

anyon

-0.70

assetsadobe

-0.69

ocre

-0.68

asel

-0.65

 ammon

-0.65

 ethics

-0.65

POSITIVE LOGITS

beat

1.43

Beat

1.39

 Beat

1.31

rice

1.15

riz

1.10

cade

1.01

down

0.97

terness

0.94

nik

0.94

rix

0.93

Activations Density 0.006%

phrases related to the Beatitudes

occurrences of the word "Beat" or variations of it in different contexts

No Comments

No Known Activations