INDEX

Explanations

phrases related to transgender individuals

oai_token-act-pair · gpt-3.5-turbo

references to transgender individuals and issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

steen

-0.77

spring

-0.74

 Kers

-0.70

 Lans

-0.68

 Manufacturer

-0.67

 Rove

-0.65

akings

-0.65

fare

-0.64

eon

-0.64

 reper

-0.63

POSITIVE LOGITS

gender

1.14

 transsexual

0.89

 transgender

0.89

sexual

0.88

 genital

0.87

istors

0.85

 genders

0.82

genic

0.81

 bathroom

0.80

 restroom

0.79

Activations Density 0.015%

phrases related to transgender individuals

references to transgender individuals and issues

No Comments

No Known Activations