INDEX

Explanations

differences between policies or practices among different entities, particularly related to real estate or entertainment venues

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

quel

-0.79

seed

-0.78

teenth

-0.73

sis

-0.72

sha

-0.71

doms

-0.71

luaj

-0.67

tan

-0.67

ynes

-0.67

plets

-0.66

POSITIVE LOGITS

 venue

1.06

 venues

0.97

 hosting

0.83

 seating

0.81

goers

0.81

 booked

0.81

 patrons

0.75

 booking

0.75

 occupancy

0.74

 frequ

0.73

Activations Density 0.038%

differences between policies or practices among different entities, particularly related to real estate or entertainment venues

No Comments

No Known Activations