INDEX

Explanations

proper nouns

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

 pigeon

-0.76

 pige

-0.70

matic

-0.64

 apes

-0.63

 avenues

-0.62

 Zeit

-0.62

é¾įå¥ĳå£«

-0.62

 Pictures

-0.61

 avoidance

-0.60

 Norn

-0.60

POSITIVE LOGITS

ï¸ı

0.99

ever

0.88

âĶĢâĶĢ

0.86

ternity

0.86

âĶĢâĶĢâĶĢâĶĢ

0.83

ield

0.82

uthor

0.81

_>

0.77

arthed

0.76

\-

0.75

Activations Density 0.135%

proper nouns

No Comments

No Known Activations