INDEX

Explanations

references to religious or sacred terminology

oai_token-act-pair · gpt-3.5-turbo

the term "Holy" and its variations, indicating a focus on religious concepts or institutions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

phrine

-0.88

atown

-0.87

PsyNetMessage

-0.82

yrinth

-0.79

ickr

-0.79

Downloadha

-0.73

ļéĨĴ

-0.71

wana

-0.71

apses

-0.70

xual

-0.70

POSITIVE LOGITS

 Grail

1.02

 Scripture

0.81

father

0.78

 Trinity

0.77

 Father

0.73

gra

0.73

 smokes

0.72

field

0.71

 Maiden

0.70

 Scriptures

0.69

Activations Density 0.016%

references to religious or sacred terminology

the term "Holy" and its variations, indicating a focus on religious concepts or institutions

No Comments

No Known Activations