INDEX

Explanations

brand names and product names

oai_token-act-pair · gpt-3.5-turbo

specific brands and notable entities, especially in pop culture and technology

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

gdala

-0.76

razil

-0.76

outhern

-0.75

rower

-0.75

behind

-0.73

actionDate

-0.72

uckland

-0.71

ociate

-0.71

starter

-0.70

currently

-0.69

POSITIVE LOGITS

Â®,

1.14

 Syndrome

1.07

 Medals

1.02

 bulbs

0.99

 stickers

0.98

Â®

0.97

 dolls

0.96

âĦ¢

0.96

 sneakers

0.94

 commercials

0.93

Activations Density 0.493%

brand names and product names

specific brands and notable entities, especially in pop culture and technology

No Comments

No Known Activations