INDEX

Explanations

bits and pieces of programming code, especially related to string manipulation

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

hub

-0.72

 Dong

-0.72

loc

-0.71

 Fenrir

-0.70

Rao

-0.70

shows

-0.69

ieu

-0.69

 Rodrig

-0.69

 Nare

-0.69

Hy

-0.69

POSITIVE LOGITS

avement

1.05

ãĥ´

0.95

(*

0.93

catentry

0.92

FORMATION

0.83

thood

0.83

ãĤ¯

0.82

ãĤ¼ãĤ¦ãĤ¹

0.81

 sizeof

0.80

ãĥį

0.79

Activations Density 0.038%

bits and pieces of programming code, especially related to string manipulation

No Comments

No Known Activations