INDEX

Explanations

phrases related to product manufacturing and specifications

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

mire

-0.81

izoph

-0.72

fel

-0.69

roxy

-0.68

ctica

-0.65

iggins

-0.64

 Warden

-0.64

rina

-0.64

ceed

-0.62

romy

-0.62

POSITIVE LOGITS

 brands

0.84

 headquartered

0.83

 supplying

0.81

 manufactures

0.78

 manufacturers

0.76

 manufacturer

0.74

 beware

0.74

DAQ

0.74

 supplier

0.73

hips

0.72

Activations Density 0.088%

phrases related to product manufacturing and specifications

No Comments

No Known Activations