INDEX

Explanations

mentions of the word "taxes."

oai_token-act-pair · gpt-3.5-turbo

discussions related to taxation and tax policy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Jenner

-0.73

theless

-0.70

ties

-0.69

lihood

-0.66

 Sadd

-0.65

 Encounter

-0.64

 Scouting

-0.64

Images

-0.64

Osw

-0.63

 Watts

-0.63

POSITIVE LOGITS

 levied

1.32

payer

1.27

 payable

1.25

payers

1.05

paying

1.00

 levy

0.95

 owed

0.94

 imposed

0.93

 collectors

0.93

 revenue

0.93

Activations Density 0.045%

mentions of the word "taxes."

discussions related to taxation and tax policy

No Comments

No Known Activations