INDEX

Explanations

locations and events related to crimes or accidents

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

semb

-0.72

Japan

-0.69

 orchestr

-0.68

 reperto

-0.67

 governments

-0.67

 regimes

-0.66

 vacc

-0.66

uania

-0.66

 environments

-0.65

ability

-0.65

POSITIVE LOGITS

 Avenue

1.43

 Boulevard

1.41

 Blvd

1.38

 Street

1.31

Ave

1.31

 avenue

1.26

Rd

1.24

 Parkway

1.19

 Highway

1.17

Rue

1.10

Activations Density 1.000%

locations and events related to crimes or accidents

No Comments

No Known Activations