INDEX

Explanations

references to women or females in various contexts, such as combat roles, management positions, cosmetic surgery, and political preferences

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.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

REDACTED

-0.89

UFF

-0.81

-+-+

-0.76

RAY

-0.75

ebus

-0.74

REC

-0.72

EMA

-0.71

æĸ¹

-0.71

rador

-0.70

eme

-0.70

POSITIVE LOGITS

folk

1.24

 empowerment

1.03

 genital

0.99

opausal

0.94

 breasts

0.93

 menstru

0.92

hood

0.87

 contraceptive

0.87

 reproductive

0.86

volent

0.83

Activations Density 0.071%

references to women or females in various contexts, such as combat roles, management positions, cosmetic surgery, and political preferences

No Comments

No Known Activations