INDEX

Explanations

reviews about products or items that were purchased with positive feedback

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 themselves

-0.75

-0.70

Their

-0.69

 omin

-0.68

 Their

-0.67

 Plaint

-0.66

Assad

-0.63

 disputed

-0.62

idates

-0.62

 respectively

-0.62

POSITIVE LOGITS

 myself

1.79

my

1.20

 blogging

1.01

 researching

0.95

 browsing

0.81

 crochet

0.81

 photograp

0.80

 writing

0.79

 cowork

0.79

 reluct

0.78

Activations Density 4.987%

reviews about products or items that were purchased with positive feedback

No Comments

No Known Activations

reviews about products or items that were purchased with positive feedback

No Comments

No Known Activations