INDEX

Explanations

mentions of statistics related to performance or rankings

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_fs6144-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

6,144

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

 feces

-0.63

irie

-0.62

ĸļ

-0.60

 levers

-0.58

 uncond

-0.57

 Guatem

-0.57

 Mankind

-0.57

 respir

-0.56

é¾

-0.56

vironment

-0.56

POSITIVE LOGITS

 metic

0.81

warts

0.80

amic

0.78

omes

0.66

mort

0.64

mology

0.64

riter

0.62

acia

0.62

Yang

0.60

essen

0.60

Activations Density 0.829%

mentions of statistics related to performance or rankings

No Comments

No Known Activations