INDEX

Explanations

phrases related to actions, strategies, and gameplay in a gaming context

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

onics

-0.30

seys

-0.29

 Extrem

-0.27

odes

-0.27

kins

-0.27

ikes

-0.27

independence

-0.27

keyes

-0.26

lip

-0.26

otto

-0.26

POSITIVE LOGITS

$$$$

0.31

 Slot

0.29

 Rober

0.29

 cancell

0.29

oldown

0.28

 Dull

0.25

 Holder

0.25

raint

0.25

gomery

0.25

Slot

0.25

Activations Density 7.805%

phrases related to actions, strategies, and gameplay in a gaming context

No Comments

No Known Activations