INDEX

Explanations

words related to authority, control, and power

oai_token-act-pair · gpt-3.5-turbo

phrases related to conflict, danger, and political issues

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

ggles

-0.66

 partName

-0.60

ratulations

-0.57

pires

-0.57

)\

-0.55

)!

-0.54

guyen

-0.54

>)

-0.53

 yours

-0.51

bernatorial

-0.51

POSITIVE LOGITS

 because

1.11

because

0.96

 "...

0.88

 owing

0.87

".

0.86

 whereas

0.86

0.84

 despite

0.83

but

0.83

 "âĢ¦

0.83

Activations Density 1.120%

words related to authority, control, and power

phrases related to conflict, danger, and political issues

No Comments

No Known Activations