INDEX

Explanations

instances of words or phrases followed by the word "of" to capture possessives or relationships

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

flix

-0.68

RIP

-0.66

liest

-0.65

gaming

-0.63

fuck

-0.63

Fax

-0.60

gest

-0.60

HQ

-0.60

BG

-0.59

Daily

-0.59

POSITIVE LOGITS

 sorts

1.21

 consciousness

0.78

 hostilities

0.76

 course

0.68

 theirs

0.65

 humankind

0.64

 Funds

0.63

 wills

0.63

 limbs

0.63

 mankind

0.63

Activations Density 0.126%

instances of words or phrases followed by the word "of" to capture possessives or relationships

No Comments

No Known Activations