INDEX

Explanations

mentions of personalization and customization

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cknowled

-0.89

amar

-0.77

der

-0.75

 acknowled

-0.71

ado

-0.69

uns

-0.67

eware

-0.66

isman

-0.65

ware

-0.63

guards

-0.62

POSITIVE LOGITS

 circumstances

1.00

 lifestyles

0.97

 needs

0.95

 tastes

0.94

 realities

0.89

 climates

0.89

 optimum

0.88

 strengths

0.86

 niche

0.85

 specific

0.83

Activations Density 0.251%

mentions of personalization and customization

No Comments

No Known Activations