INDEX

Explanations

words related to levels, amounts, and measurements in scientific contexts

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

mic

-0.41

ĪĴ

-0.39

soDeliveryDate

-0.37

soever

-0.36

inx

-0.35

Gi

-0.35

iot

-0.35

mer

-0.34

ington

-0.34

sid

-0.34

POSITIVE LOGITS

 concentration

0.41

 gradient

0.37

keley

0.35

elsius

0.35

 concentrations

0.34

ately

0.33

wagon

0.32

legraph

0.32

avorite

0.32

 Concent

0.31

Activations Density 3.918%

words related to levels, amounts, and measurements in scientific contexts

No Comments

No Known Activations