INDEX

Explanations

phrases related to law enforcement and criminal activities

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Scotia

-0.68

 Atmosp

-0.68

 XIII

-0.65

 Skies

-0.62

 Peoples

-0.61

 Atmospheric

-0.60

 Hyde

-0.60

 Kafka

-0.59

 Gerrard

-0.59

 Else

-0.59

POSITIVE LOGITS

ster

1.33

mers

1.28

mer

1.22

ming

1.21

sters

1.21

nor

1.14

ler

1.11

ball

1.09

elin

1.07

ner

1.06

Activations Density 2.020%

phrases related to law enforcement and criminal activities

No Comments

No Known Activations