INDEX

Explanations

references to cars and car-related events

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Seym

-0.88

 Flavoring

-0.82

é¾įå¥ĳå£«

-0.68

Kyr

-0.68

achu

-0.68

aspberry

-0.68

yip

-0.67

iversal

-0.67

scl

-0.65

utical

-0.65

POSITIVE LOGITS

 cars

1.19

 dealership

1.18

 racing

1.16

 driver

1.13

 drivers

1.12

 motorcycles

1.11

bike

1.10

 parked

1.10

ousel

1.10

cars

1.05

Activations Density 2.407%

references to cars and car-related events

No Comments

No Known Activations