INDEX

Explanations

words related to mental health conditions, especially anxiety

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

endor

-0.85

estone

-0.80

anmar

-0.78

ingen

-0.78

nice

-0.72

estones

-0.70

sites

-0.69

announced

-0.67

ded

-0.67

eve

-0.67

POSITIVE LOGITS

 disorders

1.08

 disorder

1.00

 provoking

0.96

 Disorders

0.94

 sickness

0.83

 inducing

0.81

 illness

0.81

 symptoms

0.80

 anxiety

0.80

xiety

0.80

Activations Density 0.031%

words related to mental health conditions, especially anxiety

No Comments

No Known Activations