INDEX

Explanations

information related to coding, programming, and technical instructions

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

othal

-0.45

 hallucinations

-0.45

aceae

-0.45

 scept

-0.44

 Canaver

-0.43

loss

-0.43

EW

-0.43

 decap

-0.42

 electrodes

-0.41

 pans

-0.41

POSITIVE LOGITS

 tradem

0.57

SourceFile

0.54

ĨĴ

0.52

PORT

0.51

 Telephone

0.50

âĸ¬

0.50

taboola

0.48

gmail

0.48

 pione

0.47

«ĺ

0.47

Activations Density 14.983%

information related to coding, programming, and technical instructions

No Comments

No Known Activations