INDEX

Explanations

mentions of specific monetary values

oai_token-act-pair · gpt-3.5-turbo

monetary values related to earnings and costs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 skelet

-0.75

umbn

-0.70

efer

-0.69

egu

-0.68

ullivan

-0.63

idth

-0.62

ellar

-0.62

IFE

-0.61

 timet

-0.61

ahime

-0.60

POSITIVE LOGITS

 apiece

1.36

 cents

1.28

per

1.07

($

1.03

 (Â£

1.02

 increments

1.00

-$

0.99

 sterling

0.95

 dollars

0.94

pees

0.92

Activations Density 0.035%

mentions of specific monetary values

monetary values related to earnings and costs

No Comments

No Known Activations