INDEX

Explanations

phrases related to mental health and medical consultations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vana

-1.04

ographed

-1.02

ascript

-1.00

aturation

-0.96

hammad

-0.94

acca

-0.93

ayne

-0.93

enei

-0.92

asta

-0.91

aturated

-0.89

POSITIVE LOGITS

shire

1.78

 Borough

1.32

 Crown

1.11

 Yard

1.00

 Manor

0.99

 Spit

0.99

 Hath

0.98

mouth

0.97

 Cathedral

0.95

hurst

0.95

Activations Density 2.063%

phrases related to mental health and medical consultations

No Comments

No Known Activations

phrases related to mental health and medical consultations

No Comments

No Known Activations