INDEX

Explanations

mentions of the word "God"

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "God."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Luxem

-0.72

 kindred

-0.71

 Eisen

-0.66

 Lima

-0.62

URN

-0.62

URRENT

-0.62

-0.61

Altern

-0.60

 Morales

-0.59

Hof

-0.59

POSITIVE LOGITS

frey

1.16

zilla

1.06

mother

1.06

 Almighty

1.04

 forbid

1.01

father

0.94

boss

0.91

 bless

0.91

god

0.87

osaurs

0.81

Activations Density 0.026%

mentions of the word "God"

references to the concept of "God."

No Comments

No Known Activations