INDEX

Explanations

words related to significant or central concepts or entities

oai_token-act-pair · gpt-3.5-turbo

instances of the word "hub."

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

terday

-0.80

 graded

-0.69

 Fang

-0.64

ists

-0.64

 menstrual

-0.64

 Grave

-0.63

 Painter

-0.63

 Jackets

-0.62

IGHTS

-0.62

 Overt

-0.62

POSITIVE LOGITS

bub

1.61

bard

1.40

ris

1.32

lins

1.11

bies

1.05

staff

1.04

bie

1.04

bles

1.03

lot

1.03

caps

1.02

Activations Density 0.035%

words related to significant or central concepts or entities

instances of the word "hub."

No Comments

No Known Activations