INDEX

Explanations

medical conditions and symptoms

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æ©Ł

-0.89

staff

-0.78

 Books

-0.76

 chairs

-0.76

bern

-0.75

 spons

-0.74

Oracle

-0.74

 microphones

-0.72

 desks

-0.72

maid

-0.71

POSITIVE LOGITS

ptoms

1.37

 Symptoms

1.29

 symptoms

1.28

 infections

1.13

 prevention

1.06

 outbreaks

1.05

 occur

1.04

 Detected

1.03

 epidemic

1.03

 headaches

1.01

Activations Density 3.513%

medical conditions and symptoms

No Comments

No Known Activations