INDEX

Explanations

car models and car-related terms

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

OPLE

-0.71

ivities

-0.70

 parach

-0.65

oses

-0.65

ignore

-0.63

ostic

-0.63

iveness

-0.62

thood

-0.62

 Jinn

-0.62

merce

-0.61

POSITIVE LOGITS

wark

1.10

een

1.03

eenth

0.94

nesday

0.90

0.89

cle

0.83

bit

0.82

swick

0.80

tor

0.79

eer

0.78

Activations Density 3.013%

car models and car-related terms

No Comments

No Known Activations