INDEX

Explanations

the word "Off" with the strongest activation levels

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of "off" or "offering."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

izabeth

-0.70

ridor

-0.64

growth

-0.63

 dehydration

-0.62

 skelet

-0.62

ascript

-0.61

 federation

-0.61

omething

-0.60

enment

-0.60

ATHER

-0.60

POSITIVE LOGITS

Off

3.65

Off

2.44

OFF

2.42

off

1.88

OFF

1.80

off

1.56

offs

1.36

 Offer

1.33

 Away

1.27

 Down

1.23

Activations Density 0.006%

the word "Off" with the strongest activation levels

words related to the concept of "off" or "offering."

No Comments

No Known Activations