INDEX

Explanations

definitions and explanations of variables, methods, and parameters in a codebase

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

cler

-1.03

 coli

-0.99

print

-0.98

á½

-0.98

lyn

-0.97

Beast

-0.96

à¦

-0.93

velt

-0.92

ILLE

-0.91

kus

-0.89

POSITIVE LOGITS

eters

1.23

ilitary

1.15

 parameters

1.09

staking

1.00

ftime

0.99

 flares

0.98

eers

0.96

 Param

0.95

ised

0.94

 labels

0.94

Activations Density 1.522%

definitions and explanations of variables, methods, and parameters in a codebase

No Comments

No Known Activations