INDEX

Explanations

phrases related to discrimination or support for LGBT people

oai_token-act-pair · gpt-3.5-turbo

references to LGBTQ+ individuals and issues related to their rights and treatment

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

quickShipAvailable

-0.85

Nut

-0.82

pmwiki

-0.76

tun

-0.75

aic

-0.73

inventoryQuantity

-0.72

HL

-0.72

Recomm

-0.71

SER

-0.71

BuyableInstoreAndOnline

-0.69

POSITIVE LOGITS

hood

1.11

 everywhere

0.84

 disproportion

0.84

folk

0.83

 oppressed

0.80

 disproportionately

0.80

 genital

0.80

 patriarchy

0.80

paces

0.80

 bisexual

0.79

Activations Density 0.137%

phrases related to discrimination or support for LGBT people

references to LGBTQ+ individuals and issues related to their rights and treatment

No Comments

No Known Activations