INDEX

Explanations

photo captions

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

iqueness

-0.79

 verbs

-0.72

 knees

-0.69

 objections

-0.69

 debates

-0.69

 reintrodu

-0.69

 regret

-0.65

 langu

-0.65

worms

-0.64

 allergies

-0.63

POSITIVE LOGITS

 Shutterstock

1.38

 Courtesy

1.22

 Wikimedia

1.17

 REUTERS

1.14

 Flickr

1.04

 COURT

1.04

 Getty

1.01

 Provided

1.00

 Bett

0.98

 Everett

0.97

Activations Density 0.425%

photo captions

No Comments

No Known Activations