INDEX

Explanations

questions of morality and ethical behavior within society

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

aiman

-0.67

chin

-0.65

andowski

-0.63

asio

-0.63

rev

-0.62

untled

-0.62

 Solitaire

-0.61

tall

-0.61

ropolis

-0.59

USE

-0.59

POSITIVE LOGITS

 disposable

0.95

 sacred

0.83

 equals

0.82

 expend

0.80

 objectively

0.79

Subject

0.78

 interchangeable

0.77

 unworthy

0.76

zeb

0.76

¥µ

0.75

Activations Density 0.147%

questions of morality and ethical behavior within society

No Comments

No Known Activations