INDEX

Explanations

financial terms related to loss and deficit

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

ECK

-0.82

ansky

-0.77

ENTS

-0.76

ATT

-0.76

âĸ¬âĸ¬

-0.69

raper

-0.68

rouse

-0.68

":[{"

-0.68

enegger

-0.68

andise

-0.68

POSITIVE LOGITS

 incurred

1.05

 aversion

0.97

iem

0.92

 Loss

0.90

 suffered

0.87

 loss

0.85

 inflicted

0.83

lessness

0.79

 losses

0.79

esville

0.78

Activations Density 8.392%

financial terms related to loss and deficit

No Comments

No Known Activations