INDEX

Explanations

phrases related to people joining or being joined in different settings

oai_token-act-pair · gpt-3.5-turbo

instances of people joining or participating in discussions

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

istry

-0.80

 dissip

-0.68

 abandonment

-0.64

åĮ

-0.64

å£«

-0.63

 wards

-0.63

äºº

-0.62

Sold

-0.61

 deed

-0.61

 Unicode

-0.61

POSITIVE LOGITS

podcast

1.20

odcast

1.13

 listener

1.00

 Podcast

0.95

Episode

0.94

 podcast

0.91

 listeners

0.90

 Episode

0.89

isode

0.89

 podcasts

0.87

Activations Density 0.532%

phrases related to people joining or being joined in different settings

instances of people joining or participating in discussions

No Comments

No Known Activations