INDEX

Explanations

medical terms and information

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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

 comprom

-0.74

 Quan

-0.72

isations

-0.70

izations

-0.67

 almonds

-0.66

 Oaks

-0.65

 Rapp

-0.64

 rall

-0.63

KING

-0.63

oyd

-0.62

POSITIVE LOGITS

EStream

1.00

 âĨ

0.96

 âĨĳ

0.95

idepress

0.85

<+

0.82

 CrossRef

0.82

 Âł Âł

0.81

 Âł Âł Âł Âł

0.78

 âĨĴ

0.77

+++

0.76

Activations Density 13.105%

medical terms and information

No Comments

No Known Activations