INDEX

Explanations

descriptive words and phrases related to unique and remarkable locations or places

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

bots

-0.96

 Freddy

-0.83

girls

-0.78

aughs

-0.77

Tickets

-0.77

 Agents

-0.76

©¶æ

-0.75

Attach

-0.75

mails

-0.74

Aud

-0.73

POSITIVE LOGITS

 geological

1.44

 basin

1.38

 mountainous

1.37

 volcanic

1.33

 region

1.29

 continent

1.27

 plateau

1.26

 coastline

1.25

 peninsula

1.22

 UNESCO

1.20

Activations Density 0.293%

descriptive words and phrases related to unique and remarkable locations or places

No Comments

No Known Activations