INDEX

Explanations

mentions or descriptions of people and their life events, especially related to sports and personal relationships, as well as specific events or achievements

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

 disgu

-0.83

 bids

-0.78

tox

-0.77

 craw

-0.75

 Rite

-0.75

 beetles

-0.74

 sooner

-0.74

 beds

-0.74

 rever

-0.74

 carp

-0.73

POSITIVE LOGITS

Getty

1.28

Flickr

1.16

Bloomberg

1.08

AFP

1.07

Math

1.06

Las

1.05

CBC

1.03

Courtesy

1.02

NRS

1.02

WAR

1.02

Activations Density 8.056%

mentions or descriptions of people and their life events, especially related to sports and personal relationships, as well as specific events or achievements

No Comments

No Known Activations