INDEX

Explanations

phrases related to social inclusion and exclusion

oai_token-act-pair · gpt-3.5-turbo

terms associated with social inclusion and exclusion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

à¼

-0.62

hei

-0.61

hr

-0.60

VW

-0.60

VPN

-0.60

quit

-0.60

 descended

-0.59

Temperature

-0.59

Â·Â·

-0.59

FO

-0.59

POSITIVE LOGITS

 inclusion

4.04

 omission

1.99

 exclusion

1.85

clusion

1.68

 incorporation

1.58

 insertion

1.27

 participation

1.26

 exclus

1.22

 additions

1.22

 deletion

1.21

Activations Density 0.009%

phrases related to social inclusion and exclusion

terms associated with social inclusion and exclusion

No Comments

No Known Activations