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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Lima

-0.65

 Luxem

-0.62

 Cheong

-0.61

Downloadha

-0.60

OUR

-0.59

 needle

-0.59

 Morales

-0.58

 contin

-0.58

URRENT

-0.58

ROR

-0.57

POSITIVE LOGITS

frey

1.47

father

1.30

mother

1.13

win

1.10

 bless

1.08

 forbid

1.07

 Bless

1.05

zilla

1.05

olphin

1.03

spell

1.03

Activations Density 0.044%

mentions of the word "God."

references to the concept of God

No Comments

No Known Activations