INDEX

Explanations

terms related to transgender individuals

oai_token-act-pair · gpt-3.5-turbo

mentions of transgender individuals and related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

spring

-0.91

Trust

-0.67

gio

-0.66

fare

-0.66

cv

-0.65

 Lans

-0.65

eon

-0.65

steen

-0.64

EY

-0.64

zz

-0.64

POSITIVE LOGITS

 transgender

1.22

gender

1.10

 transsexual

1.09

 Transgender

1.02

 gender

0.91

 genital

0.87

 Nadu

0.84

istani

0.80

Dys

0.79

 females

0.79

Activations Density 0.012%

terms related to transgender individuals

mentions of transgender individuals and related topics

No Comments

No Known Activations