INDEX

Explanations

gender-related characteristics and attributes, such as masculinity and femininity

oai_token-act-pair · gpt-3.5-turbo

terms that represent gender concepts, specifically masculinity and femininity

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oulos

-0.83

Assembly

-0.81

rocket

-0.75

Deal

-0.74

owitz

-0.72

Money

-0.68

 Redemption

-0.68

RAY

-0.68

DVD

-0.67

REL

-0.66

POSITIVE LOGITS

 hygiene

0.96

 masculine

0.90

 feminine

0.88

 pronouns

0.87

 femin

0.82

istries

0.80

 masculinity

0.79

inity

0.78

 mascul

0.77

WithNo

0.76

Activations Density 0.036%

gender-related characteristics and attributes, such as masculinity and femininity

terms that represent gender concepts, specifically masculinity and femininity

No Comments

No Known Activations