INDEX

Explanations

the word "offset" or variations of it

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

ovych

-0.67

 antioxid

-0.66

Interstitial

-0.66

IVERS

-0.65

emon

-0.64

ombat

-0.63

uay

-0.63

KER

-0.62

åŃ

-0.62

ĨĴ

-0.62

POSITIVE LOGITS

ting

1.55

ted

1.14

mented

1.04

ments

0.98

ment

0.92

aneous

0.85

igated

0.84

ts

0.80

cro

0.80

baugh

0.78

Activations Density 0.019%

the word "offset" or variations of it

No Comments

No Known Activations

the word "offset" or variations of it

No Comments

No Known Activations