INDEX

Explanations

mentions or references to the name "Wu."

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Wu"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

*/(

-0.85

 mileage

-0.74

 SERV

-0.71

 Essex

-0.69

 Lynd

-0.68

 Lyft

-0.65

population

-0.65

 BART

-0.64

 pige

-0.64

 Amtrak

-0.63

POSITIVE LOGITS

wu

1.22

Tang

1.21

Wu

1.08

pei

1.04

awei

1.00

qi

0.99

ikuman

0.98

wei

0.90

zi

0.90

hei

0.89

Activations Density 0.006%

mentions or references to the name "Wu."

mentions of the name "Wu"

No Comments

No Known Activations