INDEX

Explanations

numerical values related to interest rates

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

terms related to interest rates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_post

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

 Alic

-0.86

 Goose

-0.64

thur

-0.63

\\\\

-0.62

lia

-0.61

wyn

-0.59

ffe

-0.59

ãĥ¯ãĥ³

-0.59

awa

-0.59

wich

-0.58

POSITIVE LOGITS

 rates

1.33

 rate

1.22

 Rates

1.16

 payments

1.06

Rate

1.05

 expense

1.00

rate

1.00

 Rate

0.97

charge

0.93

 accrued

0.90

Activations Density 0.026%

numerical values related to interest rates

terms related to interest rates

No Comments

No Known Activations