INDEX

Explanations

numerical measurements, specifically focusing on dimensions and sizes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uscript

-0.69

ariat

-0.62

owitz

-0.60

oras

-0.59

onto

-0.59

Wiki

-0.59

Nation

-0.57

Reviewed

-0.57

Gle

-0.56

 Bagg

-0.56

POSITIVE LOGITS

 diameter

0.96

iameter

0.88

 circumference

0.77

 radius

0.76

 Seym

0.68

 tubing

0.65

rad

0.64

PVC

0.63

 measurement

0.63

 cone

0.62

Activations Density 8.572%

numerical measurements, specifically focusing on dimensions and sizes

No Comments

No Known Activations