INDEX

Explanations

codes and symbols in a programming context

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

ingham

-0.68

arming

-0.67

rament

-0.65

agonist

-0.64

oring

-0.64

anmar

-0.64

 skelet

-0.63

 Lama

-0.61

arnaev

-0.61

herty

-0.60

POSITIVE LOGITS

dayName

0.81

TPPStreamerBot

0.64

catentry

0.61

\\\\\\\\

0.61

cffffcc

0.60

\"

0.59

ricanes

0.58

yssey

0.58

oice

0.57

"""

0.56

Activations Density 6.186%

codes and symbols in a programming context

No Comments

No Known Activations