INDEX

Explanations

personal experiences and opinions, especially related to treatments or products

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

 occurs

-0.79

osate

-0.78

 Highlights

-0.75

ulence

-0.73

 Ensure

-0.73

pedia

-0.71

inav

-0.69

ossom

-0.68

urry

-0.66

izes

-0.66

POSITIVE LOGITS

 able

1.37

 afraid

1.32

 aware

1.32

 unable

1.31

 willing

1.30

 unaware

1.17

 obligated

1.17

 obliged

1.16

 interested

1.15

 glad

1.15

Activations Density 2.328%

personal experiences and opinions, especially related to treatments or products

No Comments

No Known Activations