INDEX

Explanations

mentions of people in managerial or leadership roles

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

romy

-0.77

 Leafs

-0.66

 Reincarn

-0.63

 Crimes

-0.63

 Territories

-0.62

 Revival

-0.62

 Transit

-0.61

 Sleeping

-0.60

 Kingdoms

-0.59

 Warfare

-0.59

POSITIVE LOGITS

esses

1.05

hip

0.98

urally

0.95

ess

0.91

alty

0.89

 beware

0.86

ial

0.83

essing

0.81

hesis

0.80

hips

0.79

Activations Density 2.384%

mentions of people in managerial or leadership roles

No Comments

No Known Activations