INDEX

Explanations

mentions of religious figures, specifically the Pope

oai_token-act-pair · gpt-3.5-turbo

mentions of the Pope

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

nesota

-0.79

ript

-0.77

é¾

-0.76

yrinth

-0.70

stract

-0.70

rha

-0.69

ahime

-0.68

ilater

-0.68

ÑĮ

-0.68

schild

-0.68

POSITIVE LOGITS

 Francis

1.26

 Benedict

0.96

 Clement

0.79

Father

0.79

 Pope

0.78

esses

0.78

 pope

0.77

 Father

0.75

otle

0.74

Pope

0.73

Activations Density 0.014%

mentions of religious figures, specifically the Pope

mentions of the Pope

No Comments

No Known Activations