INDEX

Explanations

adjectives related to positive attributes

oai_token-act-pair · gpt-3.5-turbo

phrases describing positive or favorable qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

çīĪ

-0.74

ulhu

-0.72

 Arabian

-0.68

 Noir

-0.66

 exacerb

-0.63

pora

-0.63

 turmoil

-0.62

 homelessness

-0.62

 veil

-0.61

 incred

-0.60

POSITIVE LOGITS

sounding

1.53

looking

1.33

enough

1.31

minded

1.27

sized

1.09

nat

1.02

named

1.00

hearted

0.98

tem

0.98

guy

0.98

Activations Density 0.076%

adjectives related to positive attributes

phrases describing positive or favorable qualities

No Comments

No Known Activations