INDEX

Explanations

phrases related to medical treatments and interventions, with a focus on treatments for specific conditions like PTSD and cancer

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hemy

-0.66

prints

-0.65

 nesting

-0.62

printed

-0.62

 compr

-0.62

lihood

-0.61

bour

-0.61

arrass

-0.60

 Geological

-0.60

erd

-0.59

POSITIVE LOGITS

 regimen

1.04

ilitating

0.97

 therapies

0.88

 treatments

0.86

 treatment

0.86

utic

0.83

 medically

0.80

 therapy

0.79

 Loving

0.77

culosis

0.76

Activations Density 0.034%

phrases related to medical treatments and interventions, with a focus on treatments for specific conditions like PTSD and cancer

No Comments

No Known Activations