INDEX

Explanations

terms related to catastrophic events or negative outcomes

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

soType

-0.72

appa

-0.71

etch

-0.69

weeney

-0.68

sheet

-0.67

 Cosponsors

-0.65

anooga

-0.65

arel

-0.65

aquin

-0.64

 referen

-0.63

POSITIVE LOGITS

 awaits

1.22

bringer

0.98

 incarn

0.95

 inflicted

0.94

 await

0.92

 havoc

0.89

 awaiting

0.85

ously

0.81

 ridden

0.80

 Incarn

0.80

Activations Density 0.799%

terms related to catastrophic events or negative outcomes

No Comments

No Known Activations