INDEX

Explanations

measurements related to speed, distance, and dimensions

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

ãĤ´ãĥ³

-1.04

Tea

-0.92

 Scrib

-0.86

 Metatron

-0.85

Crunch

-0.81

ħĭ

-0.81

 Carbuncle

-0.80

ergy

-0.79

Dys

-0.78

Asset

-0.77

POSITIVE LOGITS

 distances

1.16

 circumference

1.08

 kilometres

1.06

 kilometers

1.03

 radius

1.02

 highways

1.01

 diameter

0.99

 heights

0.94

 northwest

0.92

 intersections

0.91

Activations Density 10.465%

measurements related to speed, distance, and dimensions

No Comments

No Known Activations