INDEX

Explanations

the word "tax" or variations of it

oai_token-act-pair · gpt-3.5-turbo

keywords related to taxation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

Nag

-0.80

\\\\

-0.78

Sensor

-0.78

Ò

-0.76

Jem

-0.75

 Lyon

-0.74

 Ange

-0.72

 Klingon

-0.71

 Wond

-0.71

Sie

-0.71

POSITIVE LOGITS

payer

1.24

 taxes

1.02

tax

1.01

 taxing

0.99

onomy

0.97

onom

0.97

onomic

0.95

 collectors

0.94

payers

0.92

 levied

0.91

Activations Density 0.029%

the word "tax" or variations of it

keywords related to taxation

No Comments

No Known Activations