INDEX

Explanations

words related to American college football teams

oai_token-act-pair · gpt-3.5-turbo

references to sports teams and their affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

creen

-0.70

è¦ļéĨĴ

-0.68

lyak

-0.66

 droid

-0.63

hire

-0.63

igree

-0.63

 Luxembourg

-0.63

shift

-0.62

 Chern

-0.62

 Siberian

-0.62

POSITIVE LOGITS

 athletics

1.40

 Athletics

1.29

 University

1.23

 freshman

1.22

 athletic

1.22

 Wildcats

1.17

Football

1.17

 alum

1.16

 Bulldogs

1.14

 Athletic

1.14

Activations Density 0.147%

words related to American college football teams

references to sports teams and their affiliations

No Comments

No Known Activations