INDEX

Explanations

mentions of financial profit or loss

oai_token-act-pair · gpt-3.5-turbo

references to profit in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ennis

-0.72

uli

-0.65

gat

-0.65

elli

-0.65

archives

-0.64

ingham

-0.62

 Oral

-0.62

 hugged

-0.60

oding

-0.60

inel

-0.58

POSITIVE LOGITS

 profit

3.83

 Profit

3.05

 profits

2.73

 profitability

2.12

 profitable

2.01

profit

1.90

profits

1.85

 revenue

1.44

 greed

1.30

 revenues

1.28

Activations Density 0.007%

mentions of financial profit or loss

references to profit in various contexts

No Comments

No Known Activations