INDEX

Explanations

numerical patterns and codes in a document, possibly related to technical information or data analysis

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

 simplicity

-0.38

 outl

-0.36

lynn

-0.36

istically

-0.35

DonaldTrump

-0.33

ching

-0.32

 Veter

-0.32

 pits

-0.32

Â·Â·

-0.32

 chilling

-0.32

POSITIVE LOGITS

 partName

0.51

0.40

0.39

stadt

0.39

ÙĨ

0.37

iddler

0.36

adeon

0.36

ãĥķãĤ©

0.36

tek

0.35

system

0.35

Activations Density 6.799%

numerical patterns and codes in a document, possibly related to technical information or data analysis

No Comments

No Known Activations