INDEX

Explanations

examples or discussions related to technology and software development, particularly pertaining to coding practices and programming processes

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

illard

-0.83

older

-0.79

rongh

-0.71

oded

-0.68

 idol

-0.66

itta

-0.66

heed

-0.66

entin

-0.65

aed

-0.64

young

-0.64

POSITIVE LOGITS

 stroke

0.86

_.

0.82

 strokes

0.82

 persuasion

0.80

 intervals

0.72

Ò

0.72

 flick

0.71

tails

0.71

HCR

0.71

WARE

0.69

Activations Density 14.466%

examples or discussions related to technology and software development, particularly pertaining to coding practices and programming processes

No Comments

No Known Activations