INDEX

Explanations

descriptions of personal experiences and details

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

 remains

-0.70

ãĥ«

-0.67

stood

-0.65

ãĤ¯

-0.65

 likeness

-0.63

utterstock

-0.62

 emerges

-0.62

xit

-0.61

ppings

-0.61

ulence

-0.60

POSITIVE LOGITS

 myself

1.26

my

0.95

nesday

0.85

cember

0.81

 haha

0.78

 ðŁĻĤ

0.78

:-)

0.76

 researching

0.75

:)

0.73

(~

0.73

Activations Density 0.895%

descriptions of personal experiences and details

No Comments

No Known Activations