INDEX

Explanations

words related to vehicles, driving, and transportation

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_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

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

dress

-0.72

--------------------------------------------------------

-0.70

baugh

-0.66

 contrad

-0.60

bender

-0.59

¥µ

-0.58

manship

-0.56

ĪĴ

-0.56

alty

-0.55

heet

-0.55

POSITIVE LOGITS

arsity

1.23

isions

1.19

ancouver

1.16

ille

1.15

oodoo

1.14

ascular

1.13

irus

1.11

iolet

1.07

olution

1.06

ampire

1.06

Activations Density 3.462%

words related to vehicles, driving, and transportation

No Comments

No Known Activations