INDEX

Explanations

phrases highlighting quotes in a text

oai_token-act-pair · gpt-3.5-turbo

comma usage in quotes or direct speech

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

inary

-0.63

oin

-0.62

elong

-0.62

xes

-0.62

asted

-0.60

oros

-0.59

odes

-0.59

adies

-0.59

ORPG

-0.59

iral

-0.58

POSITIVE LOGITS

 referring

1.46

 adding

1.45

 noting

1.33

 referencing

1.31

 echoing

1.24

 citing

1.20

 quoting

1.16

 stressing

1.15

 recalling

1.15

 emphasizing

1.14

Activations Density 0.101%

phrases highlighting quotes in a text

comma usage in quotes or direct speech

No Comments

No Known Activations