INDEX

Explanations

prepositions followed by specific nouns or modifiers

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

comed

-0.67

 regards

-0.65

NS

-0.58

KK

-0.58

natureconservancy

-0.56

wcs

-0.55

 reassuring

-0.53

NW

-0.53

uilt

-0.53

Jae

-0.52

POSITIVE LOGITS

orem

0.74

iciency

0.69

eat

0.68

 choice

0.66

rage

0.65

gression

0.63

speech

0.63

parency

0.61

Lear

0.61

 Excellence

0.60

Activations Density 0.135%

prepositions followed by specific nouns or modifiers

No Comments

No Known Activations