INDEX

Explanations

technical terms related to computer programming and system management

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

hound

-0.96

staking

-0.92

terness

-0.87

EStream

-0.86

cules

-0.83

perty

-0.83

prus

-0.81

veyard

-0.81

 Moroc

-0.80

bid

-0.78

POSITIVE LOGITS

rict

1.19

alker

1.18

amped

1.15

oppers

1.14

upid

1.11

retch

1.10

alking

1.10

oppable

1.09

uffed

1.09

REAM

1.07

Activations Density 7.729%

technical terms related to computer programming and system management

No Comments

No Known Activations