INDEX

Explanations

occurrences of the word "demon" in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to demons in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ictionary

-0.75

McK

-0.74

itably

-0.72

 overw

-0.69

 airlines

-0.68

 parenting

-0.65

 padd

-0.64

IPP

-0.64

 lett

-0.64

olson

-0.64

POSITIVE LOGITS

 Demon

3.87

Demon

3.46

demon

2.53

 Demons

1.82

 Demonic

1.55

 Chaos

1.32

 demon

1.25

DEM

1.21

 Demo

1.18

DEM

1.18

Activations Density 0.018%

occurrences of the word "demon" in various contexts

references to demons in various contexts

No Comments

No Known Activations