INDEX

Explanations

references to specific words regarding nature and specific scenarios related to trees

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

glomer

-1.16

ione

-0.95

abwe

-0.88

ities

-0.87

rontal

-0.83

 Stanton

-0.83

arcer

-0.81

aleigh

-0.81

 Horowitz

-0.80

orical

-0.79

POSITIVE LOGITS

beard

1.19

 canopy

1.19

frog

1.19

yard

1.17

 trees

1.13

 tree

1.08

 trunk

1.07

©¶æ

1.04

Hug

1.04

 stump

1.04

Activations Density 1.329%

references to specific words regarding nature and specific scenarios related to trees

No Comments

No Known Activations