INDEX

Explanations

information related to software packages and installing or maintaining software on a system

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

rencies

-0.83

lasses

-0.82

iger

-0.78

trop

-0.78

lass

-0.77

RNA

-0.77

aneously

-0.76

 Schwar

-0.75

othy

-0.74

BER

-0.73

POSITIVE LOGITS

 Jessie

0.86

Whe

0.86

ership

0.76

 nomine

0.75

ione

0.73

 Inspection

0.70

Jess

0.70

é¾įå¥ĳå£«

0.69

mates

0.69

rpm

0.69

Activations Density 6.789%

information related to software packages and installing or maintaining software on a system

No Comments

No Known Activations