INDEX

Explanations

medical terms and conditions, specifically related to cancer and operations

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

 experiments

-0.71

enture

-0.71

 capacities

-0.68

 subsequ

-0.67

 campuses

-0.66

 avenues

-0.65

 acad

-0.65

 hemor

-0.64

 wallets

-0.62

 calculations

-0.60

POSITIVE LOGITS

âĢİ

0.82

jee

0.81

sama

0.75

wow

0.72

oqu

0.71

jab

0.70

Brit

0.68

-.

0.68

___

0.68

 curse

0.66

Activations Density 22.631%

medical terms and conditions, specifically related to cancer and operations

No Comments

No Known Activations