INDEX

Explanations

phrases related to military service and government controversies

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

threat

-0.73

fulness

-0.68

lihood

-0.67

livious

-0.65

RP

-0.64

URR

-0.63

ebin

-0.61

Requ

-0.60

POSITIVE LOGITS

 woman

0.95

 women

0.94

 Woman

0.85

Woman

0.80

 female

0.80

WOM

0.77

 boys

0.75

 girls

0.74

 girl

0.72

 females

0.70

Activations Density 0.131%

phrases related to military service and government controversies

No Comments

No Known Activations