INDEX

Explanations

proper nouns related to locations and names

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

UNCH

-0.68

ASED

-0.65

AAF

-0.62

CE

-0.58

 Libre

-0.58

Ø§ÙĦ

-0.57

>>>>>>>>

-0.55

IPP

-0.54

 Cout

-0.54

ãĤ´ãĥ³

-0.54

POSITIVE LOGITS

2.49

sburg

1.77

sie

1.59

sb

1.44

sd

1.42

sburgh

1.42

sis

1.41

sch

1.39

sf

1.37

ski

1.32

Activations Density 6.257%

proper nouns related to locations and names

No Comments

No Known Activations