INDEX

Explanations

dates of the week

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

åĬ

-0.73

respons

-0.71

egal

-0.68

ript

-0.66

ership

-0.66

bler

-0.65

abet

-0.65

chest

-0.64

ordes

-0.64

onne

-0.64

POSITIVE LOGITS

 afternoon

1.80

 morning

1.75

 evening

1.66

 night

1.60

 mornings

1.45

morning

1.27

 Night

1.24

 nights

1.22

 evenings

1.20

night

1.05

Activations Density 0.710%

dates of the week

No Comments

No Known Activations