INDEX

Explanations

words related to financial expenses

oai_token-act-pair · gpt-3.5-turbo

references to expenses and financial costs

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

unin

-0.84

gewater

-0.78

ezvous

-0.77

 GOODMAN

-0.73

gement

-0.68

kus

-0.64

ĨĴ

-0.64

mbuds

-0.62

vironment

-0.62

axter

-0.62

POSITIVE LOGITS

 incurred

1.30

 expenses

0.95

 reimburse

0.87

itures

0.87

 expense

0.85

 expenditure

0.82

 reimb

0.78

oided

0.77

 reimbursement

0.76

iture

0.76

Activations Density 0.018%

words related to financial expenses

references to expenses and financial costs

No Comments

No Known Activations