INDEX

Explanations

information related to programming, file systems, and data processing

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

uj

-0.67

plom

-0.60

ibur

-0.60

 Laure

-0.58

onso

-0.57

idem

-0.56

aida

-0.54

oran

-0.53

ĪĴ

-0.51

rera

-0.51

POSITIVE LOGITS

Bytes

0.70

SIZE

0.66

limit

0.62

 chunks

0.62

 integers

0.60

Limit

0.59

 limit

0.58

 size

0.57

 buckets

0.55

 percentage

0.55

Activations Density 17.508%

information related to programming, file systems, and data processing

No Comments

No Known Activations