INDEX

Explanations

phrases related to statistics and data percentages

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

ipel

-0.79

livious

-0.72

oren

-0.68

mun

-0.67

ivid

-0.65

ilitary

-0.65

asar

-0.64

rongh

-0.62

isphere

-0.62

ollen

-0.62

POSITIVE LOGITS

 Minotaur

0.71

 Shine

0.70

 Twice

0.69

TBD

0.67

 Finch

0.67

 Rails

0.66

 Heal

0.64

 equals

0.63

ãĥīãĥ©

0.63

 Evil

0.62

Activations Density 0.342%

phrases related to statistics and data percentages

No Comments

No Known Activations