INDEX

Explanations

elements related to online interaction and calls to action

oai_token-act-pair · gpt-3.5-turbo

phrases related to streaming or online content engagement

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 revers

-0.83

 dece

-0.78

 equival

-0.77

 escaping

-0.77

 actu

-0.75

 eroded

-0.75

 fleeing

-0.74

 elim

-0.73

 evapor

-0.73

 reversing

-0.72

POSITIVE LOGITS

Advertisements

1.16

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

1.13

--------------------------------------------------------

1.10

Thank

1.08

Thanks

1.04

################################

1.02

Feel

1.01

Lastly

1.01

Want

1.00

Congratulations

1.00

Activations Density 0.529%

elements related to online interaction and calls to action

phrases related to streaming or online content engagement

No Known Activations