INDEX

Explanations

proper nouns related to names and locations

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

anche

-0.77

govtrack

-0.74

gel

-0.70

antes

-0.69

uala

-0.69

RIC

-0.68

iatric

-0.67

license

-0.66

raise

-0.66

emale

-0.66

POSITIVE LOGITS

 globe

1.29

 periphery

1.23

 edges

1.20

 perimeter

1.16

 clock

1.02

 necks

0.96

 corner

0.95

 horizon

0.93

clock

0.93

 country

0.90

Activations Density 0.063%

proper nouns related to names and locations

No Comments

No Known Activations