INDEX

Explanations

numerical figures and technical terms related to technological products

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

Negative Logits

aldi

-1.02

uese

-1.00

bard

-0.93

wo

-0.90

 warr

-0.90

ding

-0.89

 distribut

-0.88

Ott

-0.87

warts

-0.86

-0.85

POSITIVE LOGITS

perture

1.07

UGE

0.99

ILS

0.91

BILITY

0.91

 Merrill

0.89

 Dragonbound

0.89

UAL

0.87

VILLE

0.86

00000000

0.84

 dating

0.83

Activations Density 0.089%

numerical figures and technical terms related to technological products

No Known Activations