INDEX

Explanations

phrases related to unity and community

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

 gratification

-0.77

quo

-0.66

 totality

-0.65

UD

-0.64

 citation

-0.63

 anonymity

-0.59

LSD

-0.59

 Publication

-0.58

 srfAttach

-0.56

 citations

-0.56

POSITIVE LOGITS

bsite

1.10

bley

1.10

akening

1.05

athered

1.05

ird

1.05

ldon

1.04

asel

1.01

eks

1.01

aving

1.00

igh

0.99

Activations Density 8.972%

phrases related to unity and community

No Comments

No Known Activations