INDEX

Explanations

references to specific events or incidents involving individuals and locations

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_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

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

 Wilmington

-0.92

 Staten

-0.88

 Monroe

-0.88

 Syracuse

-0.86

 Pittsburgh

-0.85

 Becky

-0.85

 Tacoma

-0.83

 Betsy

-0.83

 Florida

-0.83

 Beacon

-0.82

POSITIVE LOGITS

 Pradesh

1.45

 Sabha

1.43

 Sharma

1.42

jriwal

1.40

 Singh

1.39

 Punjab

1.34

 Maharashtra

1.30

umbai

1.28

 Kumar

1.28

 Modi

1.28

Activations Density 4.783%

references to specific events or incidents involving individuals and locations

No Comments

No Known Activations