INDEX

Explanations

Punctuation marks and symbols like colons and parentheses

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

 conversion

-0.85

 conversions

-0.82

 precip

-0.73

 constit

-0.71

 conver

-0.70

 vacancies

-0.70

 converted

-0.70

 embassies

-0.70

 nucleus

-0.67

 Conversion

-0.67

POSITIVE LOGITS

laughs

1.35

Laughs

1.26

lol

1.18

laugh

1.15

RIP

1.03

cue

1.02

sn

1.01

mmmm

1.01

FY

1.00

ONSORED

0.98

Activations Density 0.152%

Punctuation marks and symbols like colons and parentheses

No Comments

No Known Activations