INDEX

Explanations

terms related to control and restriction, particularly in the context of data usage and traffic management

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

itaire

-0.71

é¾įå¥ĳå£«

-0.69

ists

-0.68

 lips

-0.66

ISM

-0.66

 smack

-0.64

 Danish

-0.63

ISO

-0.63

Io

-0.62

 Clockwork

-0.62

POSITIVE LOGITS

ller

1.32

lling

1.32

llers

1.22

lled

1.10

eling

1.08

lev

1.06

lem

1.03

lish

1.02

hest

1.02

led

1.02

Activations Density 0.013%

terms related to control and restriction, particularly in the context of data usage and traffic management

No Comments

No Known Activations