INDEX

Explanations

words related to work and employment conditions, such as job satisfaction, wages, bonuses, and management practices

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_fs6144-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

6,144

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

Ń·

-0.80

 Tycoon

-0.79

Pok

-0.69

 charms

-0.68

Zar

-0.67

 Miko

-0.66

 Hazard

-0.65

 Springs

-0.64

 Quinn

-0.63

Phi

-0.63

POSITIVE LOGITS

fledged

1.44

blown

1.20

bodied

1.10

sized

1.07

scale

1.05

employment

0.99

length

0.99

strength

0.97

circle

0.96

pack

0.95

Activations Density 0.118%

words related to work and employment conditions, such as job satisfaction, wages, bonuses, and management practices

No Comments

No Known Activations