INDEX

Explanations

terms related to travel and visitor experiences

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

¶ħ

-0.74

anyahu

-0.66

 Carnegie

-0.64

ropy

-0.64

tackle

-0.62

Ĥª

-0.62

 RELE

-0.59

riad

-0.57

rd

-0.57

tery

-0.57

POSITIVE LOGITS

ibility

1.27

itors

1.12

ibly

1.09

itor

1.04

ited

0.97

vim

0.88

ibilities

0.83

itation

0.83

ually

0.83

ports

0.83

Activations Density 6.649%

terms related to travel and visitor experiences

No Comments

No Known Activations