INDEX

Explanations

phrases related to action or command verbs

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

externalActionCode

-0.91

yan

-0.67

uary

-0.63

 Examiner

-0.63

 Associated

-0.59

Legendary

-0.58

 Sample

-0.57

alias

-0.57

 Hear

-0.55

 Correspond

-0.55

POSITIVE LOGITS

 aside

0.98

 forth

0.95

 together

0.93

rescent

0.91

tin

0.89

rid

0.87

atively

0.81

tering

0.81

ronics

0.80

ongh

0.80

Activations Density 1.176%

phrases related to action or command verbs

No Comments

No Known Activations