INDEX

Explanations

references to upcoming events, releases, or premieres

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

 UNCLASSIFIED

-0.93

[*

-0.73

 Azerb

-0.72

anwhile

-0.72

pse

-0.71

theless

-0.69

ogether

-0.68

)."

-0.67

etheless

-0.67

âĹ¼

-0.66

POSITIVE LOGITS

 âĢº

0.84

 Belfast

0.78

 Donald

0.77

 âĢİ

0.72

 Posted

0.65

 cryptocurrency

0.64

 Hillary

0.62

 Updated

0.60

 frontman

0.59

 LEGO

0.59

Activations Density 3.384%

references to upcoming events, releases, or premieres

No Comments

No Known Activations