INDEX

Explanations

French words or names

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

utterstock

-1.01

ageddon

-0.92

etsk

-0.91

enged

-0.89

pread

-0.88

berra

-0.85

INESS

-0.85

 redistributed

-0.82

oppable

-0.81

ignment

-0.80

POSITIVE LOGITS

lÃ©

1.44

 Dame

1.07

 Ã©

1.06

vez

1.04

rez

1.03

mie

1.03

rÃ©

1.02

ration

1.02

itÃ©

1.01

rique

0.96

Activations Density 6.746%

French words or names

No Comments

No Known Activations