INDEX

Explanations

abbreviations and acronyms

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

ffen

-0.67

opol

-0.67

ord

-0.66

ãĥĥãĥĪ

-0.65

gaard

-0.64

adem

-0.64

iary

-0.63

king

-0.63

perties

-0.62

roman

-0.62

POSITIVE LOGITS

ELY

1.38

ER

1.34

TERN

1.32

BRE

1.31

FOR

1.30

VER

1.28

NING

1.28

FORE

1.27

IST

1.26

VEN

1.26

Activations Density 0.651%

abbreviations and acronyms

No Comments

No Known Activations