INDEX

Explanations

keywords related to religious or sacred objects or concepts

oai_token-act-pair · gpt-3.5-turbo

references to sacred or revered entities and concepts

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

 Handling

-0.73

 Tackle

-0.72

 Tacoma

-0.71

rons

-0.70

arians

-0.69

Ton

-0.67

 Ross

-0.66

atten

-0.66

produ

-0.65

 Transition

-0.65

POSITIVE LOGITS

 holy

3.62

holy

2.61

Holy

2.39

 Holy

2.26

 holiest

2.00

 sacred

1.97

 pious

1.40

 saint

1.32

 Sacred

1.32

 mystical

1.30

Activations Density 0.028%

keywords related to religious or sacred objects or concepts

references to sacred or revered entities and concepts

No Comments

No Known Activations