INDEX

Explanations

text related to computer programming, specifically in the context of coding commands and functions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gren

-0.11

inki

-0.11

endor

-0.10

"/>

-0.10

piracy

-0.10

}}

-0.10

pload

-0.10

\":

-0.10

iety

-0.10

"""

-0.10

POSITIVE LOGITS

 homophobia

0.12

 Carbuncle

0.11

*/(

0.10

akeru

0.10

 homophobic

0.10

Viv

0.10

ctor

0.10

aphael

0.10

 Ezek

0.09

dule

0.09

Activations Density 26.213%

text related to computer programming, specifically in the context of coding commands and functions

No Comments

No Known Activations