INDEX

Explanations

references to the United States

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

inventoryQuantity

-0.76

ebook

-0.71

MY

-0.69

plain

-0.68

EStreamFrame

-0.64

ucci

-0.64

 guiActiveUn

-0.64

 refres

-0.63

omez

-0.63

uberty

-0.62

POSITIVE LOGITS

 States

1.60

 Nations

1.41

 Kingdom

1.21

 STATES

1.19

 Methodist

1.10

States

1.10

 Federation

1.01

 Airlines

0.92

 State

0.86

 Nation

0.86

Activations Density 0.328%

references to the United States

No Comments

No Known Activations