INDEX

Explanations

statistical numbers related to basketball performance

oai_token-act-pair · gpt-3.5-turbo

basketball statistics related to shooting performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

MRI

-0.80

 Lerner

-0.77

Moy

-0.76

Nar

-0.74

ajor

-0.74

Sax

-0.73

utsche

-0.70

çļ

-0.70

ãĥ¯ãĥ³

-0.68

 Dresden

-0.67

POSITIVE LOGITS

 midrange

1.18

 jumper

1.04

 rebounds

1.03

 baskets

1.03

 basket

1.03

dun

0.99

rim

0.99

 hoop

0.98

pointers

0.98

 drib

0.97

Activations Density 0.158%

statistical numbers related to basketball performance

basketball statistics related to shooting performance

No Comments

No Known Activations