INDEX

Explanations

words related to social and political critique

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

iste

-0.65

ylon

-0.65

exist

-0.62

olor

-0.60

hya

-0.60

Mine

-0.59

atl

-0.57

GMT

-0.56

 Blazers

-0.56

lass

-0.55

POSITIVE LOGITS

 putting

1.46

 letting

1.45

 gaining

1.43

 sending

1.42

 creating

1.41

 maintaining

1.40

 finding

1.40

 getting

1.39

 committing

1.39

 releasing

1.38

Activations Density 1.857%

words related to social and political critique

No Comments

No Known Activations