INDEX

Explanations

phrases related to varied or different types or instances of occurrences

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

NER

-0.80

ESE

-0.78

nothing

-0.77

atown

-0.75

brance

-0.70

hire

-0.70

otto

-0.69

ISA

-0.69

instead

-0.69

ney

-0.68

POSITIVE LOGITS

 iterations

1.32

 facets

1.31

 kinds

1.28

 incarn

1.27

 aspects

1.24

 types

1.22

 sclerosis

1.22

 ways

1.21

 avenues

1.21

 occasions

1.20

Activations Density 0.657%

phrases related to varied or different types or instances of occurrences

No Comments

No Known Activations