INDEX

Explanations

names or words related to people involved in a company or organization

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically those related to names

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

ongyang

-0.69

 dispel

-0.68

cffffcc

-0.68

inal

-0.67

bably

-0.61

inally

-0.61

 surv

-0.61

 municip

-0.59

ramid

-0.59

enance

-0.59

POSITIVE LOGITS

vironment

1.33

bach

1.30

heimer

1.26

berger

1.26

holm

1.23

feld

1.22

wald

1.22

baum

1.21

hower

1.20

esis

1.19

Activations Density 0.098%

names or words related to people involved in a company or organization

proper nouns, specifically those related to names

No Comments

No Known Activations