INDEX

Explanations

information related to brain regions and functions, particularly focusing on dopamine receptors and their roles in sleep and reward processes

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

 Manor

-0.87

 Franch

-0.85

 Bans

-0.85

soDeliveryDate

-0.80

 Towns

-0.76

Weather

-0.75

 Skies

-0.75

pour

-0.74

essee

-0.73

Mist

-0.72

POSITIVE LOGITS

 neurons

1.43

 proteins

1.42

 enzyme

1.38

 neurotrans

1.38

 enzymes

1.37

 neuronal

1.37

 receptor

1.31

 inhibition

1.30

 receptors

1.29

 inhibit

1.29

Activations Density 1.386%

information related to brain regions and functions, particularly focusing on dopamine receptors and their roles in sleep and reward processes

No Comments

No Known Activations