INDEX

Explanations

references to 'Holy'

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Holy"

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

-0.99

PsyNetMessage

-0.78

xual

-0.72

ILA

-0.71

beh

-0.69

ãĤ½

-0.68

unct

-0.68

phrine

-0.68

POSITIVE LOGITS

 Grail

1.08

soever

0.85

 Holy

0.85

 Maiden

0.85

Holy

0.80

 Trinity

0.79

 Scripture

0.77

church

0.75

 holy

0.74

holy

0.73

Activations Density 0.008%

references to 'Holy'

occurrences of the word "Holy"

No Comments

No Known Activations