INDEX

Explanations

phrases containing the word "plain"

oai_token-act-pair · gpt-3.5-turbo

the word "plain" and its associations with simplicity or lack of embellishment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

glomer

-0.70

 Ascend

-0.66

vez

-0.63

waukee

-0.63

 Consumers

-0.63

uana

-0.62

hyde

-0.62

otos

-0.61

ameron

-0.61

irl

-0.60

POSITIVE LOGITS

plain

1.49

 plain

1.30

text

1.00

 Plain

0.90

ãĤ¦ãĤ¹

0.84

wallet

0.79

\\\\\\\\

0.75

face

0.70

esan

0.69

ified

0.69

Activations Density 0.005%

phrases containing the word "plain"

the word "plain" and its associations with simplicity or lack of embellishment

No Comments

No Known Activations