INDEX

Explanations

instances where a comparison is being made

oai_token-act-pair · gpt-3.5-turbo

phrases that express comparisons or similarity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

illed

-0.75

 Entered

-0.70

Published

-0.69

ogle

-0.66

ills

-0.65

neys

-0.65

kt

-0.64

ield

-0.63

=-=-=-=-=-=-=-=-

-0.62

ulations

-0.62

POSITIVE LOGITS

lihood

1.19

inyl

0.69

 convol

0.68

lier

0.65

 wildfire

0.61

 trickle

0.61

bek

0.61

yip

0.60

anism

0.60

 minded

0.56

Activations Density 0.062%

instances where a comparison is being made

phrases that express comparisons or similarity

No Comments

No Known Activations