INDEX

Explanations

the word "Watts" at varying activation values

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Watts."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 foss

-0.68

ozo

-0.66

 mort

-0.66

ournal

-0.64

 Volks

-0.62

uten

-0.61

anthrop

-0.61

erous

-0.60

arial

-0.60

 Lyft

-0.60

POSITIVE LOGITS

atts

1.19

atche

0.94

nesday

0.91

ukong

0.91

 Watts

0.86

bledon

0.85

enberg

0.82

esome

0.81

nuts

0.79

itness

0.78

Activations Density 0.037%

the word "Watts" at varying activation values

mentions of the name "Watts."

No Comments

No Known Activations