INDEX

Explanations

C++ code snippets featuring mathematical operations

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

seless

-0.87

ulence

-0.79

eness

-0.67

eless

-0.66

rup

-0.66

affles

-0.63

rolet

-0.62

iverse

-0.62

liness

-0.61

elligence

-0.61

POSITIVE LOGITS

(*

0.82

STDOUT

0.79

STD

0.76

 sizeof

0.75

 Templ

0.69

/*

0.67

VALUE

0.66

âĢ¢âĢ¢âĢ¢âĢ¢

0.65

args

0.62

bp

0.61

Activations Density 7.663%

C++ code snippets featuring mathematical operations

No Comments

No Known Activations