INDEX

Explanations

locations or proper nouns related to a specific dystopian movie franchise

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_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PORT

-0.78

 Fargo

-0.69

 Abyss

-0.66

terday

-0.65

 Millennium

-0.65

Ô

-0.63

channelAvailability

-0.62

 Sacrament

-0.62

 GOODMAN

-0.62

 Mine

-0.61

POSITIVE LOGITS

idd

1.28

inged

1.12

iddling

1.11

ashes

1.08

umbling

1.07

ented

1.07

akings

1.07

uffed

1.06

inging

1.06

ashing

1.06

Activations Density 2.321%

locations or proper nouns related to a specific dystopian movie franchise

No Comments

No Known Activations