INDEX

Explanations

terms related to property damage or destruction

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

zsche

-0.71

zee

-0.71

unin

-0.70

ullivan

-0.69

 Reloaded

-0.67

unch

-0.64

ramid

-0.63

zbek

-0.63

 Cele

-0.62

 Garner

-0.62

POSITIVE LOGITS

 inflicted

1.25

 wrought

1.17

 mitigation

0.99

 caused

0.98

 damage

0.97

 incurred

0.97

damage

0.87

 done

0.85

 sustained

0.85

 damaged

0.85

Activations Density 0.045%

terms related to property damage or destruction

No Comments

No Known Activations

terms related to property damage or destruction

No Comments

No Known Activations