INDEX

Explanations

mentions of social or political unrest and events unfolding in a specific location

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

heit

-0.74

FIELD

-0.72

isine

-0.69

ELY

-0.68

olson

-0.66

compatible

-0.66

Production

-0.66

Located

-0.65

 unless

-0.65

erate

-0.64

POSITIVE LOGITS

 debacle

1.03

 revelations

0.96

 fiasco

0.95

 Snowden

0.93

 Charlottesville

0.92

 Fukushima

0.88

 scandals

0.88

 Hebdo

0.85

 Wikileaks

0.85

 announcement

0.82

Activations Density 0.494%

mentions of social or political unrest and events unfolding in a specific location

No Comments

No Known Activations