INDEX

Explanations

words related to the financial domain, possibly focusing on costs or expenses

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'f'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 paraly

-0.71

 machine

-0.71

 Lizard

-0.66

 Hole

-0.65

 Clause

-0.63

 Loyal

-0.63

 Calder

-0.62

 Machine

-0.62

 bacter

-0.61

Das

-0.61

POSITIVE LOGITS

iddling

1.44

athom

1.25

idget

1.24

MRI

1.20

rozen

1.19

letcher

1.19

auc

1.17

ractions

1.17

iddle

1.17

udge

1.16

Activations Density 0.028%

words related to the financial domain, possibly focusing on costs or expenses

occurrences of the letter 'f'

No Comments

No Known Activations