INDEX

Explanations

mentions of negative events or situations

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

 ensured

-0.74

eros

-0.72

Ĥİ

-0.71

ente

-0.70

 ensures

-0.68

©¶æ¥µ

-0.67

 maintains

-0.67

keeping

-0.66

 depended

-0.66

assisted

-0.64

POSITIVE LOGITS

 unfold

1.15

 firsthand

1.08

 afar

0.93

 VIDEOS

0.90

 resemblance

0.86

 closely

0.80

 silhou

0.79

 replay

0.78

 similarities

0.78

ideos

0.76

Activations Density 3.817%

mentions of negative events or situations

No Comments

No Known Activations