INDEX

Explanations

specific elements or patterns in computer programming code, such as keywords related to error handling, code structure elements, and code string manipulation

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

venants

-0.68

oin

-0.61

acles

-0.60

omorphic

-0.60

acle

-0.58

otype

-0.57

cium

-0.54

asel

-0.54

uron

-0.53

velt

-0.53

POSITIVE LOGITS

++

0.63

>>\

0.60

+=

0.57

ilight

0.56

onga

0.55

[[

0.54

Skip

0.54

tsky

0.53

++)

0.53

 chop

0.52

Activations Density 7.415%

specific elements or patterns in computer programming code, such as keywords related to error handling, code structure elements, and code string manipulation

No Comments

No Known Activations