INDEX

Explanations

terms related to financial concepts, especially focusing on the word "net."

oai_token-act-pair · gpt-3.5-turbo

references to 'net' in financial or statistical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Barcl

-0.75

 Frie

-0.73

 Kits

-0.70

Pax

-0.68

 annexed

-0.65

 Abbey

-0.65

axter

-0.65

 Slov

-0.62

 Valiant

-0.62

ensitive

-0.61

POSITIVE LOGITS

izens

1.36

izen

1.28

tle

1.23

anyahu

1.21

 neutrality

1.02

flix

0.97

ting

0.94

her

0.93

runner

0.89

ted

0.88

Activations Density 0.008%

terms related to financial concepts, especially focusing on the word "net."

references to 'net' in financial or statistical contexts

No Comments

No Known Activations