INDEX

Explanations

language related to government policies and regulations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Bos

-0.73

 Salam

-0.69

Yao

-0.68

 Pony

-0.66

 Towers

-0.65

 Crusader

-0.65

 Typhoon

-0.64

 Rocket

-0.64

 Turtle

-0.63

 Droid

-0.63

POSITIVE LOGITS

rogens

1.06

rogen

1.03

 nurture

0.84

 manipulate

0.84

rew

0.84

 refine

0.82

 distribute

0.81

 execute

0.79

/+

0.78

 analyze

0.78

Activations Density 3.109%

language related to government policies and regulations

No Comments

No Known Activations