INDEX

Explanations

prepositions and phrases indicating the capability or capacity of something

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

DragonMagazine

-0.79

 ILCS

-0.73

minus

-0.66

Sport

-0.65

isms

-0.64

scene

-0.61

olitical

-0.61

lass

-0.61

falls

-0.61

udo

-0.60

POSITIVE LOGITS

 preserving

1.44

 obtaining

1.41

 keeping

1.41

 delivering

1.40

 acquiring

1.36

 converting

1.35

 maintaining

1.34

 extracting

1.34

 completing

1.34

 restoring

1.33

Activations Density 1.477%

prepositions and phrases indicating the capability or capacity of something

No Comments

No Known Activations