INDEX

Explanations

words related to physical activity and movement

oai_token-act-pair · gpt-3.5-turbo

actions related to physical activities and oppositional terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 "...

-0.84

BBC

-0.75

 transsexual

-0.69

 ......

-0.69

"...

-0.68

 waterfall

-0.65

 rituals

-0.64

 Artemis

-0.63

REDACTED

-0.62

 Bethlehem

-0.62

POSITIVE LOGITS

ÂŃ

1.97

âĢĲ

1.30

 ÂŃ

1.29

âĢĳ

1.20

Â»

1.19

.—

1.14

âĢ

1.01

îĢ

1.01

âĢ²

1.01

Â«

0.97

Activations Density 0.064%

words related to physical activity and movement

actions related to physical activities and oppositional terms

No Comments

No Known Activations