INDEX

Explanations

quotes or statements attributed to individuals, particularly with names that include prefixes like "O'"

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

isode

-0.68

 Libyan

-0.63

 copy

-0.62

 screen

-0.61

redients

-0.61

 semic

-0.60

 venture

-0.60

JC

-0.60

 RESP

-0.59

ãĥ¼ãĥĨãĤ£

-0.59

POSITIVE LOGITS

ĸļ

1.32

¡

1.30

¬

1.28

ħ

1.25

Ń

1.22

³

1.21

ı

1.21

į

1.20

º

1.19

£

1.19

Activations Density 0.133%

quotes or statements attributed to individuals, particularly with names that include prefixes like "O'"

No Comments

No Known Activations