INDEX

Explanations

names of locations or addresses

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

ult

-0.80

 acron

-0.79

 transm

-0.74

 silhou

-0.73

 person

-0.72

 prost

-0.71

 RELE

-0.71

 excuses

-0.71

 penet

-0.70

 photoc

-0.69

POSITIVE LOGITS

atown

1.29

apan

1.10

opolis

1.09

apolis

1.04

erville

1.02

area

0.99

gettable

0.98

abama

0.96

querque

0.95

borough

0.95

Activations Density 0.082%

names of locations or addresses

No Comments

No Known Activations