INDEX

Explanations

images and descriptions of real-world objects or locations

oai_token-act-pair · gpt-3.5-turbo

references to media sources and images

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

stood

-0.70

phas

-0.66

 nesting

-0.64

\)

-0.64

ongo

-0.63

incarn

-0.61

 epoch

-0.60

naires

-0.60

"),

-0.60

 Rails

-0.59

POSITIVE LOGITS

 IMAGES

1.20

 Photo

0.95

 Shutterstock

0.91

 photo

0.91

 Everett

0.90

 Wikimedia

0.90

tesy

0.88

 PHOTO

0.87

utterstock

0.87

photo

0.87

Activations Density 0.194%

images and descriptions of real-world objects or locations

references to media sources and images

No Comments

No Known Activations