INDEX

Explanations

terms related to taxation

oai_token-act-pair · gpt-3.5-turbo

phrases related to tax deductions and tax-exempt status

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 ingred

-0.66

 diam

-0.64

 Elements

-0.62

 marrow

-0.62

KN

-0.62

 sensations

-0.61

 Liver

-0.61

 Kern

-0.60

 Ital

-0.60

Hoo

-0.60

POSITIVE LOGITS

exempt

1.41

free

1.26

payer

1.22

related

1.21

protected

1.20

adjusted

1.18

funded

1.17

resistant

1.16

paying

1.15

efficient

1.14

Activations Density 0.045%

terms related to taxation

phrases related to tax deductions and tax-exempt status

No Comments

No Known Activations