INDEX

Explanations

references to computer memory and data handling concepts

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

kef

-0.99

OPLE

-0.94

yright

-0.93

jon

-0.91

doms

-0.89

 Grimm

-0.89

 Foley

-0.85

cliffe

-0.84

zag

-0.83

keye

-0.82

POSITIVE LOGITS

 consolidation

1.06

 storage

1.02

 allocation

1.01

 bandwidth

0.99

 allocations

0.94

 dumps

0.94

 retrieval

0.92

 chips

0.92

 disposal

0.89

 GDDR

0.87

Activations Density 7.061%

references to computer memory and data handling concepts

No Comments

No Known Activations