INDEX

Explanations

numeric comparisons, specifically instances where one value is multiple times larger than another value

oai_token-act-pair · gpt-3.5-turbo

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

isson

-0.82

behind

-0.80

perse

-0.76

artifacts

-0.74

fy

-0.72

bay

-0.72

among

-0.70

VPN

-0.69

galitarian

-0.69

 alike

-0.68

POSITIVE LOGITS

 usual

1.26

 amount

1.20

 allowable

1.14

 maximum

1.14

 average

1.10

 median

1.07

 original

1.06

 rate

1.04

sum

1.04

 lowest

1.02

Activations Density 0.119%

numeric comparisons, specifically instances where one value is multiple times larger than another value

No Comments

No Known Activations